Lever Ops Control Plane

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden for behavioral disclosure. It only identifies the endpoint and purpose, but does not mention side effects, idempotency, permissions, response format, or the fact that it is a mutating write. The term 'maintenance' is vague and fails to disclose the operational impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately names the API endpoint and high-level purpose. It is front-loaded and free of filler. However, its extreme brevity relies on external documentation ('documented Lever endpoint') and omits necessary context, making it efficient but not fully self-contained.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

As a mutation tool with no annotations and no output schema, the description is incomplete. It does not explain the write nature, governance parameters (reason, confirm, dry_run), or the relationship to sibling tools. Users would need to consult external docs or infer behavior from the schema alone, which is insufficient for correct and safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds minimal meaning beyond the schema by hinting at the purpose of the 'body' parameter (contact/source/tag maintenance), but it does not elaborate on how parameters interact or provide examples. The schema already documents all parameters adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool calls the Lever POST /opportunities/:opportunity/addLinks endpoint for 'contact/source/tag maintenance.' This specifies the verb (POST), resource (opportunity links), and general purpose. However, it does not explicitly differentiate from the similar sibling tools add_opportunity_sources and add_opportunity_tags, which also handle links of a specific type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the sibling tools add_opportunity_sources or add_opportunity_tags, nor are any exclusions or alternative recommendations given. The phrase 'for opportunity contact/source/tag maintenance' implies a use case but does not clarify the distinction from the more specific add-tool siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only states the HTTP method (POST) and the vague goal of 'maintenance.' It does not disclose that this is a mutating operation, any permission requirements, idempotency, or effects on existing opportunity data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the API endpoint. It is concise with no unnecessary words, but it sacrifices detail for brevity. Acceptable structure for a one-liner.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 6 parameters, no annotations, and no output schema, the description is inadequate. It does not explain the request body format, when to use the tool, or what the response will contain. The reliance on external API knowledge makes it incomplete for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds no parameter information. The body parameter is open-ended (additionalProperties: {}), and the description does not clarify the expected structure for addSources (e.g., list of sources). The schema's own descriptions cover parameter purposes adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact API endpoint (POST /opportunities/:opportunity/addSources) and associates it with opportunity contact/source/tag maintenance, which distinguishes it from siblings like add_opportunity_tags and remove_opportunity_sources. However, 'maintenance' is vague and does not explicitly say 'adds sources'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool vs. alternatives. It does not mention related tools like add_opportunity_tags or remove_opportunity_sources, nor does it state conditions for use or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility for behavioral disclosure, but it only states the endpoint and a vague purpose. It does not mention side effects (e.g., tags are added, not replaced), authentication requirements (perform_as), or any write confirmation behavior that the schema hints at via confirm and dry_run parameters. The phrase 'contact/source/tag maintenance' could even mislead about actual behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, achieving conciseness. However, the inclusion of 'contact/source/tag maintenance' is somewhat redundant and confusing, detracting from the otherwise efficient structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a mutation tool with 6 parameters, including a free-form body, and no annotations or output schema. The description fails to explain the body format, the effect of adding tags, potential side effects, or the meaning of perform_as, reason, confirm, and dry_run in context. It is too minimal for an operation of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description itself adds no parameter details beyond what the schema provides. While the schema contains descriptions for each parameter, some are generic (e.g., body is 'JSON body to send to the documented Lever endpoint'), and the description does not clarify expected body structure or parameter relationships.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool calls the Lever POST /opportunities/:opportunity/addTags endpoint and mentions tag maintenance, distinguishing it from sibling tools like add_opportunity_links and add_opportunity_sources. However, the phrase 'opportunity contact/source/tag maintenance' is ambiguous, as it could imply handling contacts and sources as well, which muddies the specific purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., remove_opportunity_tags, add_opportunity_links). The description does not mention prerequisites, conditions, or exclusions, leaving the agent to infer usage from the endpoint name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only names the API endpoint and does not disclose side effects, permission requirements, data mutation behavior, or any constraints. The tool name implies a write operation, but the description adds no behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and is brief, but it is under-specified. It provides an API endpoint mapping without supporting context, making it as close to boilerplate as possible. While concise, it lacks the informative content that would make every word valuable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters, a nested body object, no output schema, and no annotations. The description does not explain what the request body should contain, how options are structured, or what the response will be. It fails to provide sufficient context for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage of parameter descriptions, including types, defaults, and required fields. The description adds no additional parameter meaning, but the high schema coverage satisfies the baseline. The body parameter remains an opaque object, but the schema already states it is the JSON body to send.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the specific Lever endpoint (POST /requisition_fields/:id/options), which indicates the operation, but it does not explain in plain terms that the tool adds options to a requisition field. It is somewhat vague and does not distinguish from analogous tools like update_requisition_field_options or delete_requisition_field_options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It merely says 'for recruiting operations,' which is too broad and does not specify scenarios, prerequisites, or exclusions. No sibling differentiation is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full transparency burden. It correctly identifies the action as a create-operation, but omits critical details such as side effects, permission requirements, reversibility, or response behavior. The description does not go beyond stating the obvious mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—two sentences that immediately state the purpose and then reinforce it with an authoritative note. Every word serves a purpose, and the structure is front-loaded with the action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, a nested body object, no annotations, and no output schema, this description is under-equipped. It does not explain the expected return value, error cases, or how the body should be structured beyond the API endpoint. For a complex write operation, more behavioral and usage context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all six parameters, so the baseline is 3. The description adds no parameter-level detail beyond what the schema already provides, and the schema descriptions are adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Apply to a Lever posting' with the specific API endpoint. It uses a distinct verb+resource pair and mentions the documented create-application path, setting it apart from sibling tools like create_opportunity or get_posting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'This is the documented create-application path' implies this is the intended method for applying to a posting, providing clear context. It does not explicitly list alternatives or when-not-to-use scenarios, but the purpose is distinct enough that no exclusions are necessary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description was expected to disclose behavioral aspects such as side effects, authorization needs, or error conditions. It only mentions the HTTP endpoint, offering no additional transparency about the operation's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very brief and front-loaded with the endpoint, but it is too sparse to be appropriately informative. It wastes no words, yet the single sentence provides minimal value beyond the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of six parameters, a nested body object, and no output schema, the description fails to explain what a feedback template is, how to structure the body, or any constraints. It is incomplete for a tool with such requirements.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific meaning beyond the schema, but the schema already documents all six parameters, including template_id being unused for create operations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly indicates this creates a feedback template via the Lever POST /feedback_templates endpoint. It identifies the specific verb and resource, distinguishing it from sibling tools like create_form_template or create_opportunity_feedback, though it does not explicitly define what a feedback template is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context. The phrase 'for recruiting operations' is vague and does not clarify scenarios or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose side effects, permissions, and mutation behavior, but it only instructs to use the endpoint. It does not state that this is a write operation, whether it is reversible, what happens on duplicate creation, or required auth context. The creating nature is implied but not explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler: 'Use Lever POST /form_templates for recruiting operations.' It is concise and structured, though it sacrifices necessary detail for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write operation with no annotations, no output schema, and nested objects in the schema, the description is too sparse. It does not explain what a form template is, what the response looks like, error/failure behavior, or required permissions. The generic 'recruiting operations' adds little context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of the 6 parameters with descriptions, so the baseline is 3. The description adds endpoint context but no additional parameter semantics beyond what the schema already provides. It does not hurt or help beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact endpoint (POST /form_templates) and domain ('recruiting operations'), which clearly implies creating a form template and distinguishes it from sibling get/list/update/delete form_template tools. However, it never explicitly uses the verb 'create' or states the outcome, relying on REST semantics and the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like create_feedback_template or create_opportunity_form. 'for recruiting operations' is generic and does not specify prerequisites, typical scenarios, or when not to use it. Only the tool name and endpoint imply the usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that it creates an opportunity, but does not mention side effects, required permissions, rate limits, or the shape of the request body. This is insufficient for a mutation tool with no safety annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence conveys the essential purpose and endpoint. No filler or repetition; every word serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, no annotations, and a critical body parameter that is open-ended. The description does not explain what the response looks like, what fields are required in the body, or any limitations or preconditions. This leaves a significant gap for an agent to correctly construct and invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides descriptions for all 5 parameters (100% coverage), so the description does not need to add basic parameter semantics. However, the body parameter is a generic JSON object with no field structure, and the description does not compensate by hinting at required opportunity fields. The baseline 3 is appropriate since the schema handles the parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create'), the resource ('a Lever opportunity'), and the specific endpoint ('POST /opportunities'). This distinguishes it from sibling tools like create_opportunity_note or create_posting, which target different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description does not mention related tools for creating notes, feedback, or other sub-resources, leaving the agent to infer context from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It fails to mention that this is a write operation, requires perform_as, or relies on confirm/dry_run controls. It provides no information about side effects, notifications, or errors. The phrase 'for recruiting operations' is too broad to inform an agent of what happens when this tool is called.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and is front-loaded with the endpoint, so it is short and does not waste words. However, it is under-specified and lacks actionable details, making it closer to a placeholder than a useful description. It does not earn its place because it adds little beyond the tool name and endpoint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex mutation tool with 7 parameters, a nested body object, and no annotations or output schema. The description is far too sparse to guide an AI agent; it omits expected return values, error behavior, prerequisites, and examples. An agent cannot understand what the tool does, when to use it, or how to construct the body from the description alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, which meets the baseline of 3 even though the tool description adds no parameter information. The schema itself gives some meaning to each parameter, but the 'body' parameter is described only as 'JSON body to send to the documented Lever endpoint,' which is vague and does not explain the required structure. Nevertheless, the description does not need to compensate given the high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the Lever API endpoint 'POST /opportunities/:opportunity/feedback' and mentions recruiting operations, which gives some indication of the tool's scope. However, it does not explicitly state that this creates an opportunity feedback record, relying on the tool name and HTTP method for that inference. It also does not distinguish this from sibling tools like create_opportunity_note or create_feedback_template, leaving the purpose vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives such as create_opportunity_note or update_opportunity_feedback. The description only says 'for recruiting operations,' which is generic and gives no context about prerequisites, candidate selection, or when not to use it. There is no mention of exclusions or preferred alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses only that this is a creation operation via POST, which is already obvious from the name and schema. It does not mention side effects, required permissions, whether the form replaces an existing one, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the core action and endpoint. It is appropriately sized with no unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having six parameters, a nested body object, and no output schema, the description lacks crucial context such as what a 'profile form' is, any prerequisite conditions, return values, or error handling. It is too sparse to fully guide an agent invoking this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds no additional parameter-level meaning, but the schema already provides sufficient information for the six parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create a Lever profile form') and the target resource (specific opportunity via the endpoint). It distinguishes from sibling tools like create_form_template by explicitly pointing to the per-opportunity form endpoint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as create_form_template or other create_* tools. There is no mention of prerequisites, exclusions, or context where this tool should be preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description must carry the full behavioral disclosure burden. It only reveals the HTTP method and endpoint, implying a write operation, but does not mention required permissions, side effects (e.g., calendar invitations, notifications), reversibility, or response behavior. This is minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no wasted words and is front-loaded with the operation and endpoint. It is appropriately short, although it sacrifices informative content for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool with seven parameters, a nested body object, no annotations, and no output schema, this description is far too sparse. It references the endpoint but fails to explain what an interview creation entails, what the body should contain, or what the agent should do with the response. The description is a stub rather than a complete operational guide.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all seven parameters, including opportunity_id, perform_as, and body. The description adds no parameter-level meaning, but the baseline of 3 applies because the schema handles the heavy lifting. The free-form 'body' parameter remains opaque, but that is an API documentation concern rather than a schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact Lever endpoint (POST /opportunities/:opportunity/interviews) and the sibling set includes many opportunity sub-resources, so it is clear this creates an interview for an opportunity. It could be more explicit by saying 'creates an interview,' but the HTTP method and path plus the tool name provide sufficient specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus alternatives like update_opportunity_interview, delete_opportunity_interview, or list_opportunity_interviews. The phrase 'for recruiting operations' is too generic to help an agent decide between creating, fetching, updating, or deleting an interview.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden for behavioral disclosure. It only states the action and endpoint, omitting any mention of side effects, required permissions, idempotency, or response behavior. It adds no context beyond the verb 'Create' already in the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the action and includes the exact endpoint. Every word earns its place; there is no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a nested 'body' object with no schema details, no output schema, and no annotations. The description does not explain what constitutes a Lever note or how to structure the body, leaving a significant gap for an agent to invoke it correctly. The endpoint alone is insufficient for complete context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already documented. The description adds no additional meaning to the parameters, and the schema descriptions themselves are somewhat generic (e.g., body is 'JSON body to send to the documented Lever endpoint'), making this a baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a Lever note' with the exact REST endpoint, specifying both the action (create) and the resource (note). It effectively distinguishes this from sibling tools like update_opportunity_note, delete_opportunity_note, and list_opportunity_notes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage is implied by the verb 'Create' and the endpoint path, but no explicit guidance is given for when to use this tool versus alternatives. There are no prerequisites, exclusions, or conditions mentioned beyond the operation itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavior but doesn't. It doesn't mention that this is a write operation, any side effects, permissions, or what happens when invoked. 'POST' is the only hint, but it's not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It's a single sentence, but it's under-specified. Conciseness isn't just brevity; it's having every sentence earn its place. This sentence only names an endpoint, adding limited value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, nested body object) and no output schema, the description is severely incomplete. It doesn't explain what a panel is, what the body should contain, or any expected outcome.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% description coverage for all parameters, so the schema carries the burden. The description adds no additional meaning about parameters like body structure or the purpose of perform_as.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description cites an API endpoint but doesn't clearly state the tool's function (creating an opportunity panel). 'Recruiting operations' is vague and doesn't distinguish this from other create tools like create_opportunity_note or create_opportunity_interview.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There's no guidance on when to use this tool versus alternatives, nor any conditions or exclusions. It merely references an endpoint without context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, and the description only says 'Create a Lever posting via POST /postings.' It does not disclose any side effects, permission requirements, idempotency, or response behavior, leaving the agent without critical context for a write operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 8 words, zero filler, perfectly front-loaded. The description is appropriately sized and structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has five parameters and no output schema or annotations, yet the description is a bare one-liner. It does not explain the purpose of the body, the perform_as requirement, or the effects of dry_run and confirm, leaving the description insufficient for a complex creation operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter described (body, reason, confirm, dry_run, perform_as). The description adds no parameter information, but the schema already thoroughly documents them, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (create) and resource (Lever posting) with the HTTP method and endpoint, distinguishing it from sibling tools like update_posting and get_posting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No mention of when to use this tool versus alternatives; no exclusions or alternative tool references are given. The description provides no contextual guidance for selecting this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full transparency burden. It mentions POST, indicating a write operation, but does not disclose side effects, required permissions, error behavior, or that it creates a new requisition. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words, but it is under-specified rather than effectively concise. It lacks essential information that would make the brevity valuable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 parameters, no annotations, and no output schema, the description is critically incomplete. It does not explain what a requisition is, what the body should contain, the outcome of the operation, or when to use dry_run/confirm. The agent would be left guessing on how to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. However, the description adds no meaning beyond the schema. The 'body' parameter is generically described as 'JSON body to send to the documented Lever endpoint' without explaining requisition-specific fields, and the description does not compensate for this vagueness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the Lever POST /requisitions endpoint, implying the tool creates a requisition, but the phrase 'for recruiting operations' is broad and doesn't explicitly state the action. It also fails to distinguish this tool from siblings like create_posting or create_opportunity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided for when to use this tool versus other create tools. The description offers no context about prerequisites, conditions, or alternatives, leaving the agent without direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only indicates that this is a POST (write) operation to Lever, but it does not disclose permissions, side effects, reversibility, or return behavior. It also fails to clarify that this creates a new requisition field, which is important context for a mutating action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence with no filler. It front-loads the endpoint (Lever POST /requisition_fields) and keeps the context minimal. Every word earns its place, making it highly concise even though it lacks depth in other dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a complex API wrapper with a nested body parameter and no output schema, so the description needs to explain what a requisition field is, what the body should represent, and what happens after execution. The description provides none of that; it only names the endpoint and a vague domain, leaving the agent under-equipped to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-level meaning beyond the schema; in particular, the 'body' parameter remains an opaque JSON object with additionalProperties allowed, and the description does not explain what fields the body should contain for requisition field creation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the exact Lever endpoint (POST /requisition_fields), which maps clearly to the tool's name and creation intent. However, it does not explicitly use the verb 'create' and provides no differentiation from sibling tools like update_requisition_field, delete_requisition_field, or add_requisition_field_options. 'For recruiting operations' is a vague domain qualifier.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given for when to use this tool versus related siblings such as add_requisition_field_options, update_requisition_field, or delete_requisition_field. The only context is the broad phrase 'for recruiting operations,' which does not help an agent decide between alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full behavioral disclosure burden. It only mentions 'POST', implying a write, but discloses no side effects, permissions, idempotency, or required prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, but it is under-specified. It lacks meaningful structure or detail, so this is not effective conciseness but rather a failure to convey necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters, a nested object, no output schema, and no annotations, the description must explain behavior, return values, and usage context. It does none of this, making the tool poorly specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no parameter meaning beyond the schema, but the schema itself is sufficient, yielding the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'Use Lever POST /users for recruiting operations.' It identifies an endpoint but does not state the actual action (creating a user) or scope. It is vague and fails to distinguish from sibling tools like update_user or deactivate_user.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With many sibling tools for user management, no exclusions or preferred contexts are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description alone must disclose side effects. It only states the action and HTTP method, without mentioning that by default it executes a real write (as per the 'confirm' and 'dry_run' parameters), any authorization requirements, or expected consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that immediately states the verb and resource, with no filler words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a nested body parameter and no output schema, but the description does not explain how to construct the body, what a webhook is, or what the response contains. This is insufficient for a non-trivial creation operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage on all five properties, including descriptions for body, reason, confirm, dry_run, and actor_id. The description adds no further parameter-specific details, so the schema carries the full load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Create' and names the resource 'Lever API webhook' along with the HTTP endpoint, clearly distinguishing it from sibling tools like delete_webhook, update_webhooks, and list_webhooks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for creating webhooks but does not explicitly state when to use it versus alternatives like update_webhooks or delete_webhook. No prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries full responsibility for behavioral disclosure. It only references an API endpoint and says nothing about effects of deactivation, reversibility, required permissions, or side effects. For a write operation, this is a critical gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is concise in length, but it lacks essential explanatory content. It is under-specified rather than efficiently structured, providing no real value beyond the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and six parameters, the tool requires a richer description to be safely invokable. The description does not explain what the tool returns, when it should be used, or the consequences of deactivating a user, leaving the agent without necessary context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema documents all six parameters with clear descriptions, so schema coverage is 100%. The description adds no extra parameter-level context, but the schema already does the heavy lifting, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the Lever deactivate endpoint, which implies the tool deactivates a user, and the tool name reinforces this. However, it does not clearly state the action in plain language; it reads as an imperative instruction rather than a descriptive statement. It also doesn't explicitly differentiate from reactivate_user or update_user.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The phrase 'for recruiting operations' is too vague to indicate when this tool should be used, and there is no mention of alternatives or exclusions. The description fails to help the agent choose between deactivate_user, reactivate_user, and update_user.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to mention whether deletion is permanent, whether confirmation is required, any side effects, idempotency, or authorization needs. The description only points to an endpoint without explaining what happens when the tool is invoked.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words, so it is concise. However, the brevity sacrifices substance; it provides barely more than the tool name and endpoint. A concise but insufficient description is not ideal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool lacks an output schema and annotations, so the description must provide context about return values, success/failure behavior, and operational semantics. It does not. The description simply states the endpoint and parameterized context is absent, leaving the agent without enough information to safely and correctly use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters have descriptions in the schema. The tool description adds no additional meaning beyond the schema, which is sufficient to meet the baseline. However, some parameter descriptions (e.g., body) are vague, but this is not the description's fault.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the Lever DELETE endpoint and resource, but it reads more as a command to use the API than a functional statement of what the tool does. It distinguishes the resource (feedback templates) but does not clearly say 'deletes a feedback template' or describe the outcome. The verb is implied by the HTTP method, not explicitly stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives (e.g., create_feedback_template, update_feedback_template) and no exclusions or prerequisites. The phrase 'for recruiting operations' is too generic to help an agent decide between deletion and other operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates destructiveness via 'DELETE' but does not mention consequences, reversibility, authorization requirements, or the safety parameters like confirm and dry_run that appear in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the endpoint, which is efficient. However, it is under-specified and could convey the same information with added clarity about the operation and safety considerations without becoming bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description must provide comprehensive context. It fails to explain return values, error behavior, deletion semantics, or the role of required parameters, leaving a six-parameter destructive mutation tool significantly under-explained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all parameters including template_id and actor_id. The description itself adds no parameter-specific meaning beyond the endpoint reference, making the baseline score appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific Lever endpoint 'DELETE /form_templates/:id', which clearly indicates a delete operation on form templates and distinguishes it from sibling tools like create_form_template, update_form_template, get_form_template, and list_form_templates. It lacks a plain-language statement like 'Deletes a form template,' but the endpoint reference is specific enough to identify the resource and action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is the generic phrase 'for recruiting operations,' which applies to all Lever tools and offers no differentiation. It does not explain when to delete versus update/create a form template, nor does it mention prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions the HTTP method DELETE, which signals deletion, but it does not state whether the action is permanent, requires specific permissions, or has other side effects. This is a significant gap for a destructive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and very brief, which is concise, but it sacrifices substance for brevity. It does not earn its place as the primary descriptor, as it essentially restates the endpoint without adding useful detail. A slightly longer, more informative description would still be concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a destructive mutation tool with 7 parameters, no annotations, and no output schema, yet the description only provides the endpoint path. It is entirely inadequate for understanding the tool's behavior, side effects, or return values. The tool complexity demands a much more complete description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides descriptions for all 7 parameters (100% coverage), so the baseline is 3. The description adds a small amount of context by mapping the endpoint placeholders :opportunity and :record to opportunity_id and record_id, but it does not explain parameters like perform_as, confirm, or dry_run. Overall, the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the exact DELETE endpoint for feedback, which implies deleting opportunity feedback, but it does not explicitly state the action in plain terms. It distinguishes from sibling tools by naming the feedback resource, but the phrasing 'Use Lever DELETE ... for recruiting operations' is more of an instruction than a clear description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like delete_opportunity_note or delete_opportunity_interview. The phrase 'for recruiting operations' is too generic and does not offer context, prerequisites, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only restates the delete action and endpoint, without disclosing consequences like irreversibility, required permissions, or what happens to the file. This is a notable gap for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that states the operation and endpoint directly. No unnecessary words or repetition—highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with 7 parameters and no annotations or output schema, this description is too brief. It omits behavioral context, success/error behavior, and prerequisites, leaving the agent to infer critical details from the schema and endpoint path alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 7 parameters are documented in the input schema with descriptions, so schema coverage is 100%. The description adds no parameter-specific context, but the baseline of 3 applies because the schema handles parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Delete' and identifies the resource 'Lever opportunity file' with the exact DELETE endpoint, clearly distinguishing it from sibling tools like download/get/list/upload opportunity file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus alternatives, such as upload_opportunity_file or list_opportunity_files. Usage is only implied by the name and delete semantics, with no exclusions or alternative references.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility for behavioral disclosure. It only mentions DELETE, implying destructiveness, but does not state irreversibility, side effects, or any required confirmation. No additional context is provided beyond the endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence that leads with the endpoint path, containing no extraneous wording. However, it is so concise that it lacks substantive detail, though the structure itself is clean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters, no annotations, and no output schema, the description is far from complete. It does not explain return values, error conditions, or the impact of deleting an interview, leaving the agent to infer the tool's contract from the endpoint alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The path template adds slight value by mapping record_id to the interviews/:record segment, but the description does not elaborate on parameter usage or relationships beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the HTTP DELETE method and targeted resource (opportunity interviews) via the path template, but essentially restates the tool name. It does not provide a functional definition like 'Deletes a specific interview from an opportunity' or distinguish itself from other delete tools beyond the resource name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as update_opportunity_interview or delete_opportunity_panel. The phrase 'for recruiting operations' is too generic and does not indicate scenarios where deletion is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only states the HTTP method (DELETE) but does not disclose permanence of deletion, side effects, idempotency, or any error behavior that may occur.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that efficiently conveys the action and endpoint without any filler or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is sufficient for a simple delete operation but lacks context about consequences (e.g., permanence), expected response, or any warnings. Given the presence of a 3-parameter requirement and no output schema, a bit more detail would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides complete descriptions for all 7 parameters, so the tool description does not need to add parameter detail. Baseline of 3 is appropriate given the high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete'), the resource ('a Lever note'), and the exact HTTP endpoint, distinguishing it from sibling tools like get_opportunity_note, list_opportunity_notes, and update_opportunity_note.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for deleting a specific note on an opportunity but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives or prerequisites such as checking whether the note exists.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full behavioral burden, but it only reveals the HTTP DELETE method, implying destructiveness. It doesn't disclose irreversibility, side effects, permissions, or consequences for related data, which is significant for a deletion tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single terse sentence, which is concise and front-loaded. However, the phrase 'for recruiting operations' is generic filler, and the description is under-specified as a standalone explanation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a destructive mutation tool with no annotations and no output schema, so the description should provide more operational context. It doesn't mention return values, errors, or what deletion means for the opportunity, making it incomplete for an agent to invoke confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the baseline is 3. The description adds no parameter meaning, but the schema already documents all 7 parameters, including required fields and defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the DELETE endpoint and resource, making it clear the tool deletes an opportunity panel. However, the phrasing 'Use Lever DELETE ... for recruiting operations' is vague and doesn't explain the action in natural language or distinguish it from other delete_* sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool instead of alternatives like update_opportunity_panel or list_opportunity_panels. It only says 'for recruiting operations,' which applies to all sibling tools and offers no exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It fails to mention that this is a destructive, likely irreversible action, that confirm and dry_run parameters exist for safety, or any perform_as implications. The description is silent on side effects, making it dangerously opaque for a delete operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and contains no redundancy. However, it is under-informative and the phrase 'for recruiting operations' adds no value. It is concise in words but lacks meaningful content, earning a middle score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with six parameters, no annotations, and no output schema, this description is severely incomplete. It does not explain the deletion scope, the effect of confirm/dry_run, the purpose of body/reason, or any expected consequences. The schema documents parameters but not the operational context, leaving the agent with insufficient information to use the tool safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage with descriptions for all six parameters, so the baseline is 3. The description adds no additional parameter context, but since the schema already documents each parameter thoroughly, no deduction is warranted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the Lever DELETE /requisitions/:id endpoint, clearly indicating a deletion operation on requisitions. It distinguishes from siblings like create_requisition or update_requisition by referencing the HTTP DELETE method and resource. However, 'for recruiting operations' is vague and does not explicitly state that a requisition is deleted, leaving slight ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs alternatives. The description does not mention prerequisites, permissions, safety checks, or situations where other tools (e.g., archive or update) would be more appropriate. It merely instructs to use the endpoint for 'recruiting operations,' which is too generic to guide selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention that the operation is destructive, does not explain any safety mechanisms like confirm or dry_run, and does not state consequences of deletion. The only hint is the HTTP method 'DELETE', but the impact and reversibility are left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no fluff, which is concise. However, it is under-specified and does not convey enough meaning. It is not a waste of words, but it could be more informative while still being concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This tool has six parameters, no annotations, and no output schema, making the description crucial for context. The minimal text does not cover return values, safety behavior (confirm/dry_run), prerequisites, or any side effects. For a destructive tool, this is a significant gap that leaves the agent without enough information to invoke it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% description coverage, so the baseline is 3. The description adds no parameter-specific information, but every parameter already has a clear description in the schema. Thus, the description does not need to compensate, and the schema adequately handles parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description references the exact Lever endpoint DELETE /requisition_fields/:id, which gives a specific resource and HTTP method. However, it does not explicitly state the tool's function in business terms (e.g., 'Delete a requisition field') and does not distinguish it from similar delete tools like delete_requisition. This is more informative than a pure tautology but still vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. The phrase 'for recruiting operations' is too broad and does not specify conditions, prerequisites, or exclusions. There is no mention of when to choose this over delete_requisition or delete_requisition_field_options.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention that this is a destructive operation, whether it is reversible, what happens to associated data, or any side effects. The only hint is the HTTP DELETE method in the endpoint reference, which is not a description of behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, so it is concise. However, it is not well-structured as a description; it reads as an instruction to use an endpoint. It is not front-loaded with a clear purpose and the information it provides (API path) is already implied by the tool name and schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters, no output schema, and no annotations. The description does not explain return values, error behavior, or the specific effect on requisition field options. It is insufficiently complete for a destructive operation, especially without annotations to clarify safety.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all 6 parameters, including record_id and perform_as. The description adds no parameter information beyond the schema, so the baseline of 3 applies. It does not clarify how parameters map to the endpoint or any constraints beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Use Lever DELETE /requisition_fields/:id/options for recruiting operations' does not explicitly state what the tool does. It references an HTTP method and endpoint path but lacks a clear action verb like 'delete' or 'remove' and does not describe the resource being modified. It is closer to a command than a purpose statement, and it does not distinguish itself from siblings like delete_requisition_field or update_requisition_field_options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The phrase 'for recruiting operations' is too generic and does not specify context, prerequisites, or exclusions. No sibling alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full behavioral burden. It adds the specific HTTP method and the restriction to API-created webhooks, but it does not disclose permanence, permission requirements, or error behavior, which are relevant for a deletion operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with the verb and resource, containing zero unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives the core purpose and the schema documents all parameters, but with no output schema and no annotations, it lacks return-value expectations, error scenarios, and explicit destructive implications. This is adequate but not rich.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter already has a description. The tool description does not add any parameter-specific detail; baseline 3 is appropriate when the schema carries the parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (delete), the target resource (one Lever API-created webhook), and the REST endpoint, distinguishing it from sibling tools like create_webhook and list_webhooks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when a specific webhook must be removed, but it does not explicitly contrast with update_webhooks or list_webhooks, nor does it mention prerequisites or when not to use this action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. It mentions the GET method and base64 output, but omits critical behavior such as the need for acknowledge_sensitive_data for sensitive files, the reason requirement, and any permission or error context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with a clear verb and resource, no redundant phrasing, and front-loads the key action and endpoint. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters including a sensitive-data acknowledgment flag and a reason field, yet the description only summarizes the operation. It does not explain return structure, prerequisites, or handling of large/sensitive downloads, making it under-specified for the full context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides descriptions for 5 of 6 parameters (83% coverage), and max_bytes has min/max/default constraints. The description adds no parameter-level meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action—'Download one Lever opportunity file'—and identifies the exact endpoint and response format (base64). It clearly distinguishes from sibling tools like download_opportunity_resume by focusing on generic opportunity files.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as download_opportunity_resume or download_opportunity_offer_file. The intended context is implied only by the tool name and endpoint, leaving the agent to infer which download tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavior fully. It mentions only the download action and base64 format, but omits side effects, permission requirements, sensitivity handling (acknowledge_sensitive_data), and error behavior. It does not contradict annotations, but it is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the verb 'Download', and includes the essential attributes. No redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations. The description does not explain return structure, error conditions, or critical invocation details such as acknowledging sensitive data for certain downloads, despite having 7 parameters. An agent would need to infer too much from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 86%, so most parameters are already documented. The description adds no parameter-level detail beyond the status condition ('sent or signed') which is already in the schema enum. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action (download), resource (Lever offer file), conditions (sent or signed), format (base64), and HTTP endpoint. The name and description distinguish it from sibling tools like download_opportunity_resume and download_opportunity_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or alternative guidance. The description only states what the tool does, not when to select it over sibling download tools. The status enum is implied but not presented as usage criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for behavioral disclosure. It does mention the return format (base64) and HTTP GET, but omits critical context such as the need for actor_id, reason, and the acknowledge_sensitive_data flag for high-sensitivity downloads. The schema describes acknowledge_sensitive_data as required for sensitive data, yet the description does not surface this behavioral requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the action and resource, and includes the endpoint for immediate clarity. No filler words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters, no output schema, no annotations, and sibling tools exist, the description is insufficiently complete. It does not explain the return structure beyond 'base64', nor does it indicate when to choose this download endpoint over get_opportunity_resume or list_opportunity_resumes. The sensitivity handling and actor/reason requirements are unmentioned, leaving the agent without adequate context to invoke the tool correctly in many situations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 83% (5 of 6 params documented). The description adds the URL template that implies opportunity_id and resume_id are path parameters, which aligns with schema. However, it does not elaborate on the purpose of actor_id, reason, max_bytes, or acknowledge_sensitive_data beyond what the schema already says. Baseline of 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Download one Lever resume file'), the format ('base64'), and the exact endpoint path with opportunity and resume IDs. This distinguishes it from sibling tools like download_opportunity_file or get_opportunity_resume.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or which sibling tools to use instead (e.g., get_opportunity_resume for metadata). The description only states the mechanism, not the selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It merely restates the action and provides no context about return format, authentication, or error behavior. It is not misleading but adds minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no redundant words. It is front-loaded and appropriately sized for a simple getter, though it could benefit from a bit more contextual detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema. The description is minimal but adequate for the core action; however, it does not explain what the response contains or any related context, making it average.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully documents the single parameter with the description 'Lever archive reason ID.' The tool description adds no additional parameter semantics, so the baseline 3 applies due to high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and the resource 'Lever archive reason,' and the singular 'one' distinguishes it from the sibling list_archive_reasons.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit usage guidance is provided, but the phrasing 'one ... reason' implies it should be used when a specific archive_reason_id is known, contrasting with the sibling list tool. Lacks explicit alternatives or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals a non-obvious default behavior (omitting name, headline, emails, phones) and the requirement for detail_profile=full with a reason. This is valuable context, though it does not cover permissions, errors, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the core purpose and then adding one crucial behavioral detail. Every word earns its place with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get tool with three parameters and no output schema, the description covers the key non-obvious behavior (default field omission and full detail requirement). It does not explain why a reason is needed or what happens when a contact is not found, but these are not critical for basic usage. The description is sufficiently complete for an agent to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, but the description adds meaning by linking detail_profile=full to the need for a reason and explaining the consequence of the default operational profile. This goes beyond simply restating parameter names and provides behavioral context for the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Retrieve one Lever contact' with a specific verb and resource. It distinguishes itself from sibling tools like update_contact and list_* by focusing on a single contact retrieval. The added detail about default output omissions further clarifies the tool's specific behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (to retrieve a contact) but does not explicitly mention alternatives or exclusions, such as using list_* for multiple contacts or update_contact for modifications. The note about needing detail_profile=full for full details provides some usage guidance, but it is not framed as an alternative comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It states 'Show', which implies a read-only operation, but does not explicitly confirm the absence of side effects, whether special authorization is required, or what the response format will be. The description is too minimal to fully inform the agent of behavioral expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence that front-loads the action and resource. It contains no fluff, no redundancy, and all words earn their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple introspection tool with no input schema and no output schema, the description tells the agent what the tool does and what it returns ('which tool families and API permissions are available'). This is sufficient for a basic understanding, though it could have explicitly stated that it returns a list or object and is read-only.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema is empty. The baseline for zero parameters is 4. The description adds no parameter-level meaning because there are none to add, and it correctly focuses on the output rather than inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Show') and clearly identifies the resource ('Lever control-plane tool families and API permissions'). This distinguishes it from the many CRUD operations on opportunities, postings, users, etc., as a meta/introspection tool. The purpose is immediately clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. However, its unique purpose as a capability discovery tool implies it should be used to check available permissions before calling other tools. No alternatives are named because none are needed, but there is no explicit usage context or exclusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses that reading this configuration requires a compliance reason and explicit sensitive-data acknowledgment, indicating a sensitive/audited operation. However, it does not describe return format or error behavior; 'Retrieve' implies read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, front-loaded sentence that states the action and necessary prerequisites with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose and prerequisites for a simple retrieval operation. With no output schema, the agent may not know the exact response shape, but all parameters are documented and the operation is straightforward enough to be largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter already has a meaningful description. The description repeats the key requirements without adding new syntactic or semantic detail beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Retrieve' and names the exact resource 'Lever diversity survey configuration for a posting', clearly distinguishing it from sibling get/list tools like get_posting or list_eeo_responses.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context for when to use the tool and states required parameters (compliance reason, acknowledge_sensitive_data=true), but does not explicitly mention alternative tools or exclusions. The resource is specific enough that the intended use is evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses that full details require a reason and detail_profile=full, but this information is already present in the schema, so the description adds limited new behavioral context. It does not mention return format, error behavior, or permissions, which would be useful for a retrieval tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise, with two sentences that convey the core purpose and a key usage detail. Every word earns its place, and it is front-loaded with the action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 params, 1 required) and the schema's rich descriptions, the description adequately covers the primary purpose and a critical behavioral nuance. The lack of an output schema means the description does not need to explain return values, though a brief note on what the default operational view returns would make it more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema; it simply repeats the need for detail_profile=full and a reason. No additional parameter semantics or examples are provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Retrieve') and resource ('one Lever feedback template'), distinguishing it from sibling tools like list_feedback_templates and create/update/delete variants. The focus on a single resource makes the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for use: retrieving a single template. It also notes that full details require detail_profile=full with a reason, guiding when and how to request complete data. However, it does not explicitly name alternative tools (e.g., list_feedback_templates for multiple templates) or state when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses that full details require detail_profile=full and a reason, which is helpful. However, it does not mention safety profile (read-only), authentication requirements, or potential errors, though 'retrieve' implies a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core purpose and includes the key constraint. There is no wasted verbiage, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, so the description should compensate by explaining return values and behavior. It only states that it retrieves a template and mentions the full-detail requirement, but does not describe what the operational vs. full response contains. Given the schema fully covers parameters, the description is minimal but workable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds a note that full instructions and fields require detail_profile=full with a reason, which reinforces the schema's existing documentation on the reason parameter. It does not add substantive new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and the resource 'one Lever profile form template', which distinguishes it from list_form_templates. It is concise and unambiguous about the tool's scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (for retrieving a single template) and provides a hint about using detail_profile=full for full details, but it does not explicitly mention alternatives or when not to use it. There is no reference to list_form_templates for listing multiple templates.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses that default output omits contact PII and that contact details require a reason, which is valuable behavioral context beyond the raw schema. However, it does not mention authentication, error cases, or any side effects (though a read tool likely has none).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary purpose. The second sentence adds a specific behavioral note without redundancy. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich schema with full parameter descriptions and no output schema, the description covers the most important behavioral nuance (PII handling) and the tool's core action. It does not elaborate on expand/include, but the schema covers those, so the description is adequate for a get tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains all 5 parameters. The description restates the detail_profile=contact behavior but adds no new semantic meaning for expand, include, or reason beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Retrieve one Lever opportunity,' which clearly states a specific verb and resource with explicit singular scope. This distinguishes it from list_opportunities (plural), get_opportunity_application, and other subresource getters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus siblings like list_opportunities or get_opportunity_application. It does provide clear parameter-level guidance about using detail_profile=contact with a reason for PII access, but tool selection is only implied by the name and description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. 'Retrieve' implies read-only, and the deprecation note is useful, but it does not mention return format, pagination, error behavior, or authentication needs. Basic transparency is present but not enriched.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary action, followed by the deprecation note. Every word earns its place; no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a 4-parameter tool with clear schema descriptions, the description provides the essential purpose and the crucial deprecation alternative. It lacks a note on detail_profile return differences, but the schema covers param meaning. Sufficiently complete for a simple retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameter descriptions already explain each field. The tool description adds no parameter-specific context, but the baseline of 3 is appropriate since the schema handles the semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Retrieve one application attached to a Lever opportunity.' It also explicitly names the preferred alternative (get_opportunity with expand=applications), clearly distinguishing this tool from get_opportunity and list_opportunity_applications.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states 'Deprecated by Lever in favor of get_opportunity with expand=applications, but maintained for backwards compatibility,' providing explicit when-to-use and when-to-avoid guidance. This directly tells the agent to prefer the alternative while acknowledging backwards compatibility.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosing behavior. It goes beyond a generic 'get' by revealing that the default output omits field values and instead includes scores, timestamps, users, and field presence. This is a valuable behavioral insight, though it does not cover error handling or authentication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly written sentence that immediately states the core purpose and a critical output trait. No filler words; every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives a key fact about default output but leaves gaps. It does not explain the 'full' detail_profile behavior, the relationship between 'reason' and detail_profile (despite schema mentioning it), or the overall response structure. For a 4-parameter tool with no output schema and no annotations, this is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage, documenting each parameter with descriptions. The description does not add meaning beyond the schema; it only restates the default output behavior linked to detail_profile, which the schema already covers. Thus baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Retrieve one Lever feedback form'), identifies the specific resource (feedback form), and distinguishes it from listing operations by emphasizing 'one'. This aligns perfectly with a single-get tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool: when you need a single feedback form identified by feedback_id. However, it does not explicitly mention alternatives like list_opportunity_feedback for enumerating forms, so it lacks explicit exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosure. It reveals important behavioral details: default output omits the download URL, and full metadata requires setting detail_profile=full along with a reason. This goes beyond the schema and helps the agent understand side effects and prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff, front-loaded with the primary purpose. Every word earns its place, and the parameter behavior is summarized efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple metadata getter, and the description covers its key behavior with no output schema present. It doesn't enumerate what 'metadata' includes, but for this simplicity, the description is sufficient for an agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the interplay between detail_profile and reason, and the consequence of the 'operational' vs 'full' setting on the output (download URL omitted by default). This supplements the schema's static descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Retrieve file metadata for one Lever opportunity file.' The verb 'Retrieve' and resource 'file metadata' are specific, and it distinguishes from sibling tools like download_opportunity_file (content vs metadata) and list_opportunity_files (one vs list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on how to use the tool, noting that the default output omits the download URL and that full metadata requires detail_profile=full. It implies the tool is for metadata retrieval, but it does not explicitly contrast with alternatives like download_opportunity_file, so it lacks explicit exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses a key behavioral nuance: default output summarizes fields without values, and full field values require a reason. This goes beyond a simple retrieval statement and informs the agent about potential authorization/input requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, concise, and front-loaded with the primary purpose. Every word adds value without unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description must convey some return behavior. It explains the two output modes (summary vs full) and the reason requirement, which covers the main nuances. However, it lacks specifics about the response structure or what the summary includes, leaving a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains each parameter. The description does not add extra meaning beyond the schema, but it does reinforce the 'reason' parameter's role in enabling full values, which is already documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Retrieve' and the specific resource 'one Lever profile form attached to an opportunity'. This distinguishes it from sibling tools like list_opportunity_forms or get_opportunity, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a specific form's details are needed, but it does not explicitly state when to use this tool versus alternatives such as list_opportunity_forms. No exclusions or alternative tool references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'Retrieve,' which essentially restates the tool's name ('get'), and adds no disclosure about return format, error behavior, or required permissions. Without an output schema, the agent has no idea what response to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. Every word earns its place: verb, resource, scope, and lookup method. It is appropriately sized for the tool's simple nature.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-ID tool with no annotations and no output schema, the description is minimally sufficient but not complete. It does not mention that the interview belongs to an opportunity (though the name implies it), nor does it describe the expected return value. The absence of output schema makes this a notable gap, though the schema covers required parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds no parameter-level meaning beyond the schema, which already documents both parameters with concise descriptions. Since schema coverage is 100%, the baseline of 3 applies; the description's phrase 'by ID' does not clarify which ID maps to which parameter, but the schema names them clearly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Retrieve' and clearly identifies the resource as 'one Lever interview,' distinguishing it from the sibling list_opportunity_interviews and other get_* tools. It explicitly states the scope ('one') and the lookup mechanism ('by ID'), making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided about when to use this tool versus alternatives like list_opportunity_interviews. The intended usage is implied from 'one' and 'by ID,' but the description does not mention alternative tools or exclusion criteria, leaving the agent to infer context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses two important behaviors: the default output is metadata-only, and full note values require detail_profile=full with a reason. This goes beyond the schema by explaining a conditional requirement. It does not cover auth, rate limits, or error cases, but for a read tool the key behavioral nuance is addressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The first sentence is a clean action statement. The second sentence provides essential behavioral detail (default vs full, reason requirement). Every word earns its place, and the structure front-loads the primary purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and no annotations, the description covers the core purpose and the most important edge behavior (full vs metadata). It omits what exactly constitutes 'metadata' vs 'full values,' and doesn't describe response format, but the default/full distinction gives enough guidance. This is complete for most agent interactions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing baseline 3. The description adds semantic meaning by linking detail_profile=full to the reason requirement, which is not captured in the schema (reason is simply optional with length constraints). This clarifies the inter-parameter dependency and raises the score to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Retrieve one Lever opportunity note,' using a specific verb ('Retrieve') and clear resource ('Lever opportunity note'). It unambiguously distinguishes this from sibling tools like list_opportunity_notes (which lists multiple) and update_opportunity_note/delete_opportunity_note. The scope is singular and precise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context on when to use the 'full' detail_profile versus the default, and notes that 'full' requires a reason. However, it does not explicitly name or exclude alternative tools (e.g., list_opportunity_notes for retrieving multiple notes). The guidance is implied rather than explicit, meriting a 4 rather than a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosing behavior. It reveals that the tool works by 'scanning the documented Lever offers list' and that the default output is limited to non-sensitive data, which adds context beyond a simple 'retrieve offer'. It does not discuss error handling or authentication, but for a read-type tool, this is reasonable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose ('Retrieve one Lever offer'), and every clause adds useful detail. There is no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what the default output does *not* contain but does not specify what it *does* contain, which is a gap given the absence of an output schema. It also does not mention error behavior or the relationship to list_opportunity_offers, making it adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add additional meaning to the parameters beyond what the schema already provides. The 'detail_profile' parameter is described in the schema with enum values, and the description does not elaborate further.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a single Lever offer for a specific opportunity, using the verb 'Retrieve' and identifying the resource. It also differentiates from siblings like list_opportunity_offers and download_opportunity_offer_file by explicitly noting what the default output does not include.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear use case: 'supports offer hygiene checks' and indicates that the default output omits offer field values, signature data, and download URLs, implying it is for quick verification rather than detailed data retrieval. However, it does not explicitly name alternative tools for those needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. 'Retrieve' implies a read operation, but the description does not explicitly state safety, permissions, or error behavior (e.g., what happens if panel not found). It adds no behavioral context beyond what the tool name already conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that efficiently conveys the action. There is no wasted text, and the structure is appropriate for the simple operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two parameters, full schema coverage, and no output schema, the description is minimally complete. It clearly states the purpose, but does not describe the return format or any caveats. For a simple get, this is adequate but leaves some gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with each parameter (panel_id, opportunity_id) having a short description. The description adds no additional parameter semantics, but the schema already provides sufficient meaning. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Retrieve') and explicitly identifies the resource ('one Lever interview panel') and its scope ('attached to an opportunity'). This clearly distinguishes it from sibling tools like list_opportunity_panels (which lists all panels) and create/update/delete_panel (which mutate panels).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a specific panel is needed (given opportunity_id and panel_id), but does not explicitly mention when to use this over alternatives such as list_opportunity_panels. No when-not-to-use or exclusions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the tool does, not what happens on success/failure, required auth, or whether the referral is nested or standalone. For a retrieve operation, this is minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, directly worded sentence with no filler. Every word contributes to meaning, making it both concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (2 required parameters, no output schema, no annotations). The description covers the core purpose, and the schema covers parameters, but the agent receives no information about return format, error cases, or relationship to list_opportunity_referrals. This is adequate but leaves identifiable gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both referral_id and opportunity_id described. The description adds no additional meaning beyond 'one referral form for an opportunity,' which matches the schema. Per the baseline rule, a 3 is appropriate since the schema already handles parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Retrieve' and names the resource 'one Lever referral form' with the scope 'for an opportunity.' This clearly identifies the action and distinguishes it from sibling tools like list_opportunity_referrals, which retrieve multiple referrals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage—'one' suggests this is for retrieving a single referral by ID—but it does not explicitly state when to choose this over list_opportunity_referrals or provide any exclusionary guidance. No alternatives are mentioned, so the usage context is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral burden. It discloses that default output omits parsed resume details and download URLs, and that full metadata requires a reason—non-obvious behavior not apparent from the schema. No contradictions exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose, and every phrase earns its place. It conveys key functional constraints without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-resource metadata retrieval with 4 params and no output schema, the description covers the essential points: what it retrieves, default omissions, and the reason condition. It lacks explicit return structure or authentication notes, but is adequate given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining why 'reason' is needed (to get full metadata) and confirming the default behavior. It does not deeply elaborate on all parameters, but it supplements the schema meaningfully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states a specific verb ('Retrieve') and resource ('resume metadata for one Lever opportunity resume'), clearly distinguishing it from sibling tools like download_opportunity_resume (downloads the file) and list_opportunity_resumes (lists resumes). The singular focus on one resume is explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context about default vs. full metadata and the reason requirement, guiding when to request full metadata. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the burden. It discloses a key behavioral trait (default omits content/salary fields) and the reason requirement for full details, which goes beyond what the name alone implies. It doesn't cover all behaviors but is sufficient for this simple getter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, followed by a crucial usage tip. No wasted words; every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given moderate complexity and no output schema, the description covers the essential caveat (default omission) and distinguishes the tool. It relies on the schema for expand/include parameter details, which is acceptable since schema descriptions are comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining the default behavior of detail_profile and why the reason parameter may be required, directly linking two parameters. This enriches the schema's static descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Retrieve one Lever posting', which clearly specifies the verb and resource. It distinguishes from list_postings by emphasizing 'one' posting, making its singular purpose evident.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context on default output omission and instructs to use detail_profile=full with a reason when full details are needed. However, it does not explicitly mention alternatives or exclusions beyond this.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'Retrieve,' which indicates a read operation, but does not disclose any details about return format, pagination, error handling, or required permissions. There is no additional behavioral context beyond the verb itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence with no wasted words. It front-loads the verb and states the target resource directly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple 1-parameter tool with no nested objects or output schema. The description states what is retrieved, which is sufficient for a straightforward getter, though it could mention that the returned data includes both questions and schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully describes posting_id as 'Lever posting ID.' (100% coverage), so the description adds no new parameter-level information. The baseline of 3 is appropriate since the schema handles the semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Retrieve' and clearly identifies the resource: 'Lever posting application questions and posting apply-form schema.' This distinguishes it from sibling getters like get_posting or get_opportunity_application.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used when you need the application questions or apply-form schema for a Lever posting, but it does not explicitly state when to use it over alternatives or any exclusions. For a simple getter, this is adequate but under-specified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the default output omits compensation band, internal notes, custom fields, and approval internals, and that full details require a reason. This is meaningful behavioral context beyond what a read-only hint would provide, though not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core action, and every phrase adds value. It is concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters and no output schema. The description, combined with the fully documented schema, provides enough context for correct invocation: it clarifies the reason requirement and default output behavior. It does not explain return value structure, but there is no output schema, so it is not strictly required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining what the default output includes/excludes (e.g., compensation band, internal notes) and that full details require a reason, which complements the schema's detail_profile and reason parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Retrieve' and names the resource 'one Lever requisition', clearly distinguishing it from list_requisitions (plural) and get_requisition_field (different resource). The additional detail about default output omissions clarifies the tool's scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states it retrieves a single requisition, which implies use when a specific requisition ID is known. It also notes that full details require a reason, giving guidance on when to provide that parameter. However, it does not explicitly name alternatives or exclusion criteria, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. It only says 'Retrieve,' which implies a read operation, but gives no details on return format, error behavior, permissions, or side effects (though likely none).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence, front-loaded with the verb and resource, with no wasted words. It is appropriately sized for the tool's simplicity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only one parameter and no output schema, the description is minimally adequate but could be more complete. It doesn't explain what 'schema' entails or what the response looks like, which would be helpful for an agent expecting to use the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter, so the schema fully documents 'requisition_field_id'. The description adds no additional meaning beyond the schema, warranting the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Retrieve') and resource ('one Lever requisition field schema'). The singular 'one' distinguishes it from sibling tool list_requisition_fields, making its scope unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the singular 'one' against the list sibling, but no explicit guidance is given about when to use this over list_requisition_fields or other alternatives. There are no stated exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden of behavioral disclosure. It only states 'Retrieve one Lever stage' and adds no information about permissions, response contents, error behavior, or side effects. The verb 'Retrieve' implies a read operation, but no other traits are disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with zero wasted words. It efficiently states the verb and object, which is appropriate for a simple get tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is under-specified for the context. There are many sibling tools, but no guidance on how this tool differs. No output schema or annotations exist, so the description should clarify what 'stage' means or what the response looks like, but it does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (the sole parameter stage_id has a description 'Lever stage ID.'). The description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Retrieve') and resource ('Lever stage'), clearly indicating a single-object fetch. It distinguishes from list_stages by the word 'one', but does not explicitly name alternatives or differentiate further.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. There is no mention of when to use this tool vs. list_stages or other get_* tools, no prerequisites, and no context about typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. It only restates the read operation and adds no context about permissions, error handling, return format, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. It is appropriately concise for a simple getter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the simple schema, the description fails to mention return value, error behavior, or usage context. With no output schema and no annotations, more detail is needed for an agent to confidently invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.