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

The description indicates a mutation operation ('create') but provides no details on side effects, authentication requirements, or constraints. With no annotations, the description carries the full burden but fails to disclose behavioral traits beyond the basic 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 extremely concise with a single sentence, which is appropriate for a simple tool. However, it could be expanded to add value without losing conciseness.

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 7 parameters, no output schema, and no annotations, the description is grossly incomplete. It does not address the purpose of parameters, return behavior, or any edge cases.

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 7 parameters with 0% description coverage. The description adds no meaning to any parameter, leaving the agent to infer usage from names alone. This is insufficient for correct invocation.

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 the resource ('custom attribute'), and specifies the scope ('in the current workspace'). It effectively differentiates from sibling tools like 'attributes_update' and 'attributes_delete'.

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 when to create versus update or delete attributes. No prerequisites or context 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?

No annotations are provided, so the description carries the full burden. It discloses that default attributes cannot be deleted, which provides some behavioral context. However, it does not mention permissions, side effects, or irreversible nature, leaving gaps.

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, using two short sentences to convey the essential action and a key constraint. No unnecessary words, front-loaded with the verb.

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 delete tool with one parameter and no output schema, the description covers the core action and a constraint. However, it omits details like return value confirmation or parameter format, which would be expected for full 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?

Schema description coverage is 0%, and the description does not explain the 'id' parameter at all. It fails to compensate for the lack of schema documentation, providing no added meaning about what the ID represents or how to obtain it.

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) and the resource (custom attribute), and distinguishes from sibling tools like attributes_create by focusing on deletion. It also specifies that default attributes cannot be deleted, adding precision.

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. It implies usage for custom attributes but lacks guidance on when not to use or compare to other attribute tools. The constraint about default attributes is helpful but not sufficient for clear differentiation.

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 the tool performs a read operation ('Get all custom attributes'), but does not mention permissions, rate limits, or response details. For a simple list tool, this is adequate but not exceptional.

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, brief sentence that is front-loaded with the key action and resource. Every word serves a purpose with no superfluous text.

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 no parameters, no output schema, and performs a straightforward list operation, the description provides all necessary information for an AI agent to understand 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 input schema has no parameters, so schema coverage is 100%. The description does not add parameter semantics because none are needed. Baseline for 0 parameters is 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 clearly states the tool retrieves all custom attributes for the workspace, using a specific verb ('Get') and resource ('custom attributes'). It distinguishes from sibling tools like attributes_create, attributes_delete, which perform different operations.

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 that this tool lists all attributes, but does not explicitly state when to use it versus alternatives. However, the context is sufficient and the sibling names make differentiation obvious.

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 only states 'update the position', implying mutation. It omits details like side effects, required permissions, position indexing, or handling of invalid IDs.

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. While efficient, it sacrifices informativeness; a slightly longer description could include parameter hints without losing conciseness.

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, the description lacks essential context such as position indexing (0-based or 1-based), whether updates are incremental or absolute, and what happens on error. The missing output schema further limits 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?

Schema description coverage is 0%, so the description should elaborate on the 'order' parameter. However, it adds no meaning beyond the schema structure, leaving the agent to deduce that each item requires 'id' and 'position'.

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 specifies that the tool updates positions for multiple attributes at once, distinguishing it from sibling tools like attributes_update which likely handles single attribute updates. However, it could be more precise by mentioning 'reorder' explicitly.

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 on when to use this tool versus alternatives like attributes_update. No mention of prerequisites or context for reordering attributes, leaving the agent to infer usage without support.

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 fully disclose behavior. It only states 'Update', which implies mutation, but does not mention side effects, permissions, merge vs overwrite, or any constraints. The agent is left unaware of important behavioral traits.

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 states the purpose concisely and is front-loaded. However, it is too brief to be fully informative; some key details about parameters or usage could be added without losing conciseness. It is adequate but not excellent.

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 (8 parameters, no output schema, no annotations, many siblings), the description is severely incomplete. It does not cover return values, error handling, prerequisites, or the effects of updates. The agent cannot fully understand how to use this tool correctly 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 0%, meaning no parameter descriptions exist, and the tool description adds no explanations for any of the 8 parameters. The agent must rely on parameter names and types only, which may be insufficient for proper usage.

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 'Update' and the resource 'existing attribute' and scopes to the current workspace. It distinguishes from siblings such as attributes_create (create), attributes_delete (delete), attributes_list (list), and attributes_reorder (reorder).

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. It does not mention prerequisites, context, or exclusions. Given siblings like attributes_create and attributes_delete, explicit usage criteria would help.

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 behavioral traits. It only states 'Delete' without elaborating on destructiveness, irreversibility, or side effects on associated resources. This is insufficient 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 concise sentence, but it is too terse and omits critical context. While not verbose, 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?

Given the lack of annotations, output schema, and parameter documentation, the description is barely adequate. It misses details on return values, error conditions, and implications of deletion.

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 0%, and the description adds no meaning to the 'id' parameter. It does not clarify that 'id' refers to the rubric ID or provide any format or usage constraints.

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 'delete', the resource 'rubric', and the scope 'from the current workspace'. This distinguishes it from sibling tools like getRubrics (retrieve) and patchRubricsid (update).

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 or when not to. It lacks prerequisites (e.g., rubric must exist, permissions needed) and does not mention alternatives or consequences of deletion.

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 merely says 'Create', which implies mutation, but provides no details on side effects, permissions, lifecycle, or what the created entity represents. The description is virtually silent on 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 short but wasteful: the first sentence is a tautology ('Create a new embed session'), and the second sentence is inaccurate. It lacks a front-loaded summary of key details like supported flows or required parameters.

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 (multiple anyOf flows, many parameters), the description is completely inadequate. It does not mention the variety of flows, the required fields in body, or what the output (session token/URL) contains. The presence of an output schema does not excuse the lack of high-level 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 0%, yet the description adds no parameter information beyond the name. It does not mention that a body is required, nor the structure of the body (actor, theme, flow, presets, etc.). The description fails to compensate for the lack of schema 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 'Create a new embed session' (verb+resource) but then incorrectly narrows the purpose to 'embed the exam generation flow', ignoring other supported flows like edit-rubric, generate-question, mark-answer, and edit-exam. This misleads the agent about the tool's actual scope and does not distinguish it from sibling tools (embedSessions_get, embedSessions_revoke).

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 does it describe the different flows or prerequisites. The agent is left without context for appropriate 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, and the description does not disclose behavioral traits such as error handling (e.g., if session not found), authentication needs, or side effects. It only states the basic 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 short sentence with no unnecessary words. However, it is so brief that it sacrifices completeness for conciseness.

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 existence of an output schema, the description does not need to explain return values. However, it lacks context about error scenarios, authorization, or typical usage, making it minimally adequate.

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 0% parameter description coverage, and the description adds no extra meaning to the 'id' parameter beyond 'by its ID'. It fails to explain what the ID represents or any constraints.

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 an embed session by its ID', specifying the action (retrieve), resource (embed session), and the key parameter (ID). It distinguishes from sibling tools like embedSessions_create and embedSessions_revoke.

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. The context implies retrieval, but there is no mention of exclusions, prerequisites, or comparison to 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 full burden. It states 'Revoke access' implying destruction but offers no details on reversibility, permissions, 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?

A single 8-word sentence is concise and front-loaded, though could include more detail without becoming verbose.

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 revoke action with no annotations, output schema, or param details, the description is insufficient. It lacks behavioral context like permanence, permissions, or error states.

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 'by its ID' to the single 'id' parameter, but schema coverage is 0% and the parameter name is self-explanatory. Baseline score of 3 as the description does not add significant value 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 uses a specific verb ('Revoke access') and resource ('embed session'), clearly distinguishing it from sibling tools like embedSessions_create and embedSessions_get.

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 when-not-to-use conditions.

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?

Without annotations, the description carries full burden but only mentions cancellation. It does not disclose side effects (e.g., partial results, resumability) or required state (e.g., job must be ongoing).

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 sentence of 13 words, concise and to the point, though it could benefit from structure like listing parameters.

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 single parameter and no output schema, the description lacks completeness: it does not explain the parameter, prerequisites, or result of cancellation, leaving critical 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?

The schema has one parameter 'id' with no description, and the tool description does not clarify what the parameter represents (e.g., exam ID, job ID), leaving ambiguity for the agent.

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 'Cancel' and the resource 'ongoing job to generate new questions for the exam using AI', differentiating it from other exam tools like 'exams_startGeneration' and 'exams_questions_generate'.

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, such as when to cancel vs. wait for completion, or any conditions like the job must be in progress.

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 behavioral traits. It only states 'create', implying mutation, but does not mention side effects, authorization needs, rate limits, or what happens to existing data. The one-sentence description fails to provide adequate transparency for a creation 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 extremely concise (one sentence), but it is under-specified for the tool's complexity (12 parameters). Conciseness should not come at the expense of clarity; here, too much information is omitted, making the description ineffective.

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 (12 parameters, no annotations, no output schema), the description is severely incomplete. It fails to cover return values, parameter details, or any contextual information needed for correct invocation. The description adds minimal value beyond the tool name.

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 12 parameters with 0% description coverage at the top level. The description does not elaborate on any parameter (e.g., name, sourceMaterialIds, subject). It adds no meaning beyond the bare verb, leaving the agent without guidance on how to populate 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 action (create) and resource (exam) with scope (within workspace). However, it does not differentiate from sibling tools like exams_duplicate or exams_import, which also create exams but from different sources. The verb 'create' is unambiguous but lacks context for selection among alternatives.

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 other exams_* tools. There is no mention of prerequisites, limitations, or alternative tools for similar tasks. The description offers no contextual help for choosing 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?

No annotations provided, so the description must convey behavioral traits. It only says 'Delete the exam' without disclosing consequences like whether it is irreversible, cascading effects on related entities (e.g., questions, sessions), or required permissions.

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, which is efficient but too minimal. It is front-loaded but lacks any structure or additional context that would help the agent.

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 deletion tool with no output schema and simple parameters, the description should at least mention that the operation is permanent or any side effects. It is insufficient for an agent to understand 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 single parameter 'id' has no description in the schema (0% coverage). The description does not explain what the id represents or what format it should be in, leaving the agent without necessary guidance.

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) and the resource (exam). It distinguishes from siblings like exams_cancelGeneration which cancel generation instead of deleting the exam. However, it is very brief and lacks any additional context.

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 on when to use this tool versus alternatives. The description does not mention when deletion is appropriate or any prerequisites, such as the exam not being in use.

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 burden. It states duplication of questions and settings but does not disclose important behaviors such as whether sessions are duplicated (even though the parameter includeSessions exists), whether the original is modified, or any 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 sentence, achieving conciseness, but it is too short given the tool has three parameters. It front-loads the purpose but omits essential parameter info, making it insufficiently 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, no annotations, and parameters with zero description coverage. The description only covers basic purpose, leaving the agent with no information on parameter semantics, return values, or error conditions, rendering it incomplete.

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 0%, and the description adds no explanation for any of the three parameters (id, name, includeSessions). The agent must guess their meaning from the schema alone, which lacks 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 verb 'Duplicate' and resource 'exam', specifying it duplicates questions and settings to a new exam, distinguishing it from sibling tools like exams_create which create from scratch.

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 over alternatives, nor any prerequisites or conditions for use. The minimal description does not help an agent decide when to invoke it.

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; the description only states the action and output format, omitting behavioral traits such as whether the operation is read-only, required permissions, or any 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 sentence with no redundancy, but adding structured information (e.g., what the ZIP contains) could improve clarity without adding much length.

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 (one parameter) and the presence of an output schema, the description provides basic completeness, but lacks mention of prerequisites or how to obtain the exam ID.

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 single parameter 'id' is not described; with 0% schema description coverage, the agent must infer its meaning from context (exam ID), which is minimal and not explicit.

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 specific action 'Export an exam' and the output format 'QTI 2.1 ZIP package', distinguishing it from the sibling tool exams_export_qti3Zip by version.

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 (to get a QTI 2.1 ZIP), but does not provide explicit guidance on prerequisites, when not to use it, 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?

No annotations are provided, and the description only states the purpose without disclosing behavioral traits such as destructive potential, read-only nature, processing time, or whether the output is a file or URL. The description fails to compensate for the missing 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?

The description is a single concise sentence that is front-loaded with the core purpose. Every word carries meaning without redundancy or 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?

Given the existence of a sibling tool for QTI 2.1, the description should differentiate or mention the specific QTI version. Also, an output schema exists but is not visible; the description should hint at the output type (e.g., file download). This leaves the agent with incomplete information for correct 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?

There is only one required parameter 'id' with no schema description coverage (0%). The description implies 'id' is the exam identifier, adding minimal context beyond the schema. For a single parameter, this is adequate but not informative about format or constraints.

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 exports an exam as a QTI 3 ZIP package, specifying the verb (export), resource (exam), and format (QTI 3 ZIP). This differentiates it from the sibling tool 'exams_export_qti21Zip' by version number.

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 on when to use this tool versus alternatives like 'exams_export_qti21Zip' or other export options. The description does not mention prerequisites, required permissions, or context for 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?

No annotations provided; description only says 'Get' with no mention of side effects, permissions, or error behavior (e.g., not found case). Minimal but sufficient for a simple 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?

Single sentence with no unnecessary words, perfectly 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?

For a simple get-by-ID tool with no output schema, the description is largely complete. It could mention what fields are returned, but the core intent is clear.

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?

Only one parameter 'id' with no additional description; schema coverage is 0%, but the parameter is self-explanatory. The description adds no extra 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 'Get a single exam by its ID' clearly states the action (get) and resource (exam), and distinguishes from sibling tools like exams_list (multiple) and exams_create/delete/update (mutations).

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 single exam ID is known, but lacks explicit guidance on when not to use it (e.g., for multiple exams use exams_list) 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?

No annotations are provided, so the description carries full burden. It indicates the tool is AI-generated and based on source materials, but does not disclose behavioral traits like whether it is read-only, requires authentication, or has any side effects. While not misleading, it lacks depth.

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 action and resource. Every word adds value, with 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 the tool's low complexity (one parameter, no output schema), the description provides a clear purpose and context. It explains the input (exam id) and output (suggestions) adequately. While more detail on return format would be helpful, the description is largely complete for its role.

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 connects the 'id' parameter to the exam by stating 'based on the source materials linked to the exam', adding meaning beyond the schema's bare 'string' type. However, the parameter is not explicitly described, and schema coverage is 0%.

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 'Get', the resource 'AI-generated suggestions for context/instructions', and the context 'based on the source materials linked to the exam'. It distinguishes this tool from siblings like exams_questions_generate which generate questions, not context suggestions.

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 suggestions for context/instructions for the exam generation prompt, but it does not explicitly state when to use it vs alternatives or provide any exclusions. Usage context is clear but guidance is minimal.

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 behavioral traits. It only says 'Create an exam by importing', omitting details on side effects, permissions, or whether source materials are copied or linked. 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?

Extremely concise (one sentence), but at the cost of omitting essential details. Conciseness without completeness reduces utility for an AI agent.

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 an import operation, the description lacks information about return values, error handling, or what happens post-import. Incomplete for a creation tool with no output 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?

Input schema has 0% description coverage; the description only hints at sourceMaterialIds with the example, but does not explain the 'name' parameter or that parameters are optional. Insufficient to guide correct parameter usage.

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 (create) and resource (exam) with method (importing source materials). Provides example in parentheses, distinguishing it from exams_create or exams_duplicate. However, 'source materials' could be more precisely defined.

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 on when to use this tool versus alternatives like exams_create, exams_duplicate, or exams_questions_import. Lacks any context about prerequisites or preferred 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 bears the full burden. It implies a read operation but does not disclose potential side effects, pagination behavior, or scope limitations beyond 'within your workspace'. This minimal disclosure results in a score of 2.

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 conveys the core functionality without any extraneous words. It is well-structured 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?

Given the simplicity of the tool (two optional parameters, no output schema), the description is adequate but lacks details about the return structure (e.g., fields, pagination). It provides enough context for basic use but is 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 coverage is 100% with clear descriptions for both parameters (folder and role). The tool description adds no additional meaning beyond what the schema already provides, yielding a 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 action 'Get a list' and the resource 'all exams within your workspace'. It is a specific verb+resource, but it does not explicitly differentiate from sibling tools like exams_get or exams_sessions_list, so it scores 4.

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. It does not mention scenarios such as filtering by folder or role, nor does it indicate when to use other list tools like exams_sessions_list.

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 must reveal behavioral traits. It only states 'Export' without clarifying side effects, permissions, or non-destructive nature. It does not confirm whether the tool alters the exam or merely generates a file, leaving behavior partially ambiguous.

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 concise at one sentence (9 words), but it sacrifices necessary detail for brevity. While it front-loads the core action, it omits critical information about parameters and output, making it borderline under-specified.

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 simple interface (one parameter, no output schema), the description should be sufficient, but it lacks details on output format selection or result behavior (e.g., file download, URL). The absence of any behavioral or output information makes it incomplete for an agent to reliably use.

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 0% description coverage for the single parameter 'id'. The description does not explain the parameter's meaning (e.g., exam ID) or expected format, relying entirely on the parameter name. The brief description fails to compensate for the lack of schema 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 tool's action ('Export an exam') and the output formats ('PDF file or Word document'). It distinguishes itself from sibling tools like exams_export_qti21Zip and exams_export_qti3Zip which export to QTI formats, 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?

The description implies usage for PDF/Word export but provides no explicit guidance on when to use this tool versus alternatives (e.g., QTI export). No prerequisites or when-not conditions are mentioned, leaving the agent to infer context from the tool name.

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, and the description fails to disclose behavioral traits such as whether the tool is synchronous, returns a result, or has any side effects. It only states it generates a question, leaving agents unaware of potential wait times or authorization needs.

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, making it concise. However, it lacks structure and does not front-load key details like required parameters or output expectations.

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 3 parameters with no descriptions, no output schema, and no annotations, the description is grossly incomplete. It fails to explain what 'id' represents or what the tool returns, making it difficult for an agent to use 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?

With 0% schema description coverage, the description must explain parameters but does not. 'id' is required but unclear (exam ID or question ID?), 'message' and 'questionType' are not explained at all, leaving the agent to guess their meaning.

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 generates a new question for an exam using an AI prompt. It distinguishes from the sibling 'exams_questions_regenerate' with the word 'new'. However, it lacks specificity about the exam context or how the AI prompt is used.

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 'exams_questions_regenerate' or 'exams_startGeneration'. There is no mention of prerequisites or context for invocation.

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 provided, so description carries full burden. It fails to mention that the tool is read-only, what happens if the question is not found, or any side effects. The minimal description does not compensate for missing 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?

The description is a single sentence, which is concise, but lacks structure and important details. It is too sparse to be genuinely helpful.

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 no output schema and the complexity of having two required IDs plus an optional format, the description is incomplete. It does not hint at return values, pagination, or error conditions.

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 descriptions for each parameter, but the description adds no additional meaning. It even misleads by implying a single ID when two are needed.

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 'Retrieve a question by its ID' but the input schema requires both an exam ID and a question ID, which is misleading. The verb 'Retrieve' is appropriate but the target is imprecisely specified.

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 on when to use this tool versus siblings like exams_questions_generate or exams_questions_import. No exclusions or alternatives 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?

No annotations are provided, so the description carries the full burden. It does not disclose behavioral details such as whether importing overwrites or appends questions, side effects on existing exam data, required permissions, or error handling. For a mutation tool, this is a significant 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 two sentences, front-loaded with the primary purpose, and wastes no words. It could be slightly more structured (e.g., separate behavior from file types) but is efficient for its length.

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 6 parameters, no output schema, and no annotations, the description should cover constraints, behavior (replace vs. merge), and potential errors. It does not mention that 'keepExistingSettings' is supported or what happens if neither 'url' nor 'content' is provided. The description is incomplete for reliable agent 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?

The schema already covers 83% of parameters with descriptions. The description adds value by clarifying supported file types and that 'content' is for exports from other systems. However, it does not explain the relationship between 'url' and 'content' or the meaning of 'keepExistingSettings' in detail. Overall, it provides marginal additional meaning.

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 the exact action ('Import questions into an exam'), the target entity ('exam'), and supported file types ('Word, PDF, Moodle quiz XML and plain text files'). This clearly distinguishes from sibling tools like exams_import (imports whole exams) and exams_questions_generate (generates questions).

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 needing to import pre-existing questions from files, but it does not explicitly state when to use versus alternatives (e.g., exams_import, exams_questions_generate) or provide any when-not-to-use guidance. The agent is left to infer context from the tool name.

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 fully convey behavioral traits. It indicates a write operation but does not disclose any side effects, permission requirements, rate limits, or the impact on the question. The behavior remains mostly opaque.

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, which is concise, but it lacks essential details for an AI agent to correctly invoke the tool. It is under-specified rather than efficiently informative.

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 3 parameters, no output schema, and no annotations, the description is woefully incomplete. An agent cannot determine the proper usage, required inputs, or expected outcomes from this 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 0%, so the description must explain parameters. It only hints that 'message' is the AI prompt but does not explain 'id' and 'questionId'. The optionality and constraints of 'message' are not clarified.

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 ('Update') and the resource ('a question') and the method ('using an AI prompt'), making the purpose understandable. However, it does not explicitly differentiate from siblings like exams_questions_generate, though the context suggests distinction.

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. There is no mention of prerequisites, conditions, or scenarios where this tool is 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a state modification (accepting suggestions) but does not disclose whether the operation is destructive, reversible, or what the effects are on the suggestions. This lack of transparency leaves the agent uninformed about potential 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 clear sentence without any redundancy. It is front-loaded with the key action. However, it could be slightly improved by including brief parameter explanations without becoming verbose, so it loses a point for being too sparse.

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 lack of output schema, no annotations, and zero parameter coverage, the description is severely incomplete. It fails to provide essential context such as parameter details, behavioral traits, return values, or usage constraints. An agent would struggle to correctly invoke this tool based solely on this 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?

With 0% schema description coverage, the description must compensate by explaining the parameters. However, it does not mention 'id' or 'sessionId' at all. The parameter names are somewhat self-explanatory but insufficient; the description should clarify which identifier corresponds to what (e.g., the exam session or suggestion). The agent has no way to know how to correctly populate these fields.

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 ('Accept all AI-generated grading suggestions') and the specific context ('for the exam session'). It effectively distinguishes from the sibling tool 'exams_sessions_acceptSuggestion' by using 'all', indicating a batch operation.

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, nor does it mention any prerequisites or conditions. It only states what the tool does without any context for appropriate use.

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?

The description only states 'Accept' which implies mutation, but provides no details on effects, permanence, or required state. With no annotations, the description fails to disclose behavioral traits.

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 unnecessary words, but is too sparse for the required 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?

Given the three parameters, no output schema, and many sibling tools, the description fails to explain the relationships between parameters or provide enough context for correct 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?

The input schema has three required parameters (id, sessionId, questionId) with no descriptions. Schema coverage is 0%, and the description adds no explanation of these fields.

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 ('Accept') and the resource ('a single AI-generated grading suggestion for the exam session'). It distinguishes from the sibling tool acceptAllSuggestions.

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 acceptAllSuggestions. No context about prerequisites or conditions is 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?

No annotations provided, and the description only states 'Remove an exam session' without disclosing permanence, cascading effects, or error conditions. For a deletion tool, this is insufficient 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 short sentence, which is concise but not informative. It front-loads the action but lacks structure or additional details.

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 no annotations, no output schema, and two undocumented parameters, the description fails to provide adequate context for correct invocation. The agent is left with ambiguity about required inputs and effects.

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?

Both parameters (id, sessionId) are untyped strings with no descriptions in schema or description. The agent cannot discern which is which (e.g., id likely refers to exam id, sessionId to the session). Schema coverage is 0%.

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 'Remove an exam session' uses a specific verb and resource, clearly distinguishing it from siblings like exams_sessions_list or exams_sessions_get. However, it could be more precise about what 'remove' entails.

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 on when to use this tool versus alternatives, prerequisites, or conditions (e.g., session must exist and not be in progress). The description lacks context for appropriate 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, the description is solely responsible for behavioral transparency. It merely says 'Edit' without disclosing side effects, whether it triggers auto-grading (though an 'autoGrade' parameter exists), or any state changes beyond the answer field.

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 concise (one sentence) but overly terse. It front-loads the purpose but omits critical details, making it less useful than a slightly longer, more informative description.

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 complex input schema (nested object, mandatory fields), no output schema, and no annotations, the description is insufficient. It does not explain return values, prerequisites, or behavior such as idempotency or update timestamps.

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 only 20% (only autoGrade has a description). The tool description adds no meaning to the parameters id, sessionId, questionId, or the nested answer object, leaving their semantics unclear.

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 ('Edit') and the resource ('a single answer in an exam session'), making the purpose straightforward. However, it does not differentiate from sibling tools that might also modify session data, such as exams_sessions_acceptSuggestion.

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 guidelines are provided on when to use this tool versus alternatives like exams_sessions_saveFeedback or exams_sessions_acceptSuggestion. The description lacks context for appropriate 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, the description carries full burden but only says 'generate feedback'. It fails to disclose side effects (e.g., whether it overwrites existing feedback), authentication requirements, rate limits, or if it is a read-only or mutation operation. The term 'generate' implies mutation, but details are absent.

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, but it is under-specified. While concise, it omits critical details that would fit in 2-3 sentences. Brevity here sacrifices usefulness.

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 generating overall feedback, the absence of output schema, annotations, and detailed description leaves the agent with insufficient context to understand prerequisites, return format, or expected behavior. The description is incomplete for effective tool selection and 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 0% with no parameter descriptions in the schema. The description does not explain what 'id' and 'sessionId' represent (likely exam or session identifiers), leaving the agent to guess. The description adds no semantic value beyond the parameter names.

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 generates overall feedback for an exam session, specifying both the action (generate) and resource (feedback for test as a whole). However, it does not differentiate from sibling tools like exams_sessions_saveOverallFeedback, which could be confused as a similar but distinct operation.

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., exams_sessions_saveOverallFeedback or per-question feedback generation). Prerequisites or context (e.g., requires answers to be present, should be called after scoring) are missing.

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 burden. It only states it gets a session, without mentioning any side effects, permissions, or data volume. This is insufficient for a mission-critical 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?

A single 14-word sentence with the verb upfront. No wasted words, perfectly 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?

For a simple retrieval tool, the description omits return format, relationship to other objects, and how to interpret the session. Given the lack of output schema and annotations, the description should provide more 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 has two required parameters (id, sessionId) with 0% description coverage, but the description does not explain the difference between them or their roles. It simply says 'by its ID' without clarifying which parameter is which, adding no value over 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 tool retrieves a single exam session by ID and defines its content as student answers. It distinguishes itself from sibling like exams_sessions_list by emphasizing 'single', though it could explicitly contrast with 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?

No guidance on when to use this tool versus siblings like exams_sessions_list or exams_get. The description implies usage when you have a session ID, but does not state 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 must disclose behavioral traits. It states 'manually create' and 'possibly from uploaded data', but does not clarify whether this is a destructive operation, required permissions, or data validation rules. This 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?

The description is a single sentence, but it is vague and does not front-load critical information. It is under-informative rather than 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?

Given the complexity of the tool (4 params, nested answers array) and lack of annotations or output schema, the description is far from complete. It omits essential details about session creation, data handling, and return values.

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 0%; the description does not explain any of the four parameters (id, studentName, source, answers). The complex answers array and enum source are left undefined, forcing the agent to rely solely on the schema without additional context.

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 it creates a session manually, possibly from uploaded data. However, the name 'import' suggests batch input, and the description lacks specificity about the tool's exact role among sibling session tools. It is not a tautology but remains 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 on when to use this tool over alternatives like exams_sessions_scan or exams_sessions_editAnswer. There is no mention of prerequisites or exclusions, leaving the agent without context for 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 bears the full burden of disclosing behavioral traits. It only states the basic operation (listing sessions) without mentioning read-only nature, permission requirements, pagination, or any 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 sentence of 14 words, front-loading the core purpose. Every word is necessary, and there is no redundant content.

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 list tool with no output schema, the description adequately conveys that the result is a list of student sessions as sets of answers. However, it omits details about response format, filtering, ordering, or pagination, which would be helpful for an 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?

The input schema has a single required parameter 'id' with 0% description coverage. The description adds meaning by implying 'id' refers to the exam ('for an exam'), but does not explicitly state that it is the exam ID or provide further semantic detail.

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 'Get' and identifies the resource as 'list of all student sessions for an exam'. It clearly differentiates from sibling tools like exams_sessions_get (single session) and exams_sessions_delete (delete) through the 'list' 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 description implies usage context (listing all sessions for an exam) but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like exams_sessions_get for retrieving a single session.

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 present, so the description must disclose behavioral traits. It indicates mutation ('Set') but does not mention permissions, idempotency, side effects, or return values. The tool may overwrite existing feedback, but this is not stated.

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. However, it lacks structural elements like a use case or example. It is appropriately sized but could benefit from a second sentence for context.

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 no output schema, the description should explain what the tool returns (e.g., success confirmation or updated object). It does not. It also omits prerequisites (e.g., session and question must exist). The information provided is insufficient for an agent to fully understand tool behavior.

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 maps high-level concepts ('feedback' and 'grade') to the parameters 'feedback' and 'pointsAwarded', but the schema already describes these with comments. With 60% schema coverage, the description adds minimal new meaning 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 clearly states the action ('Set') and the resource ('teacher feedback and/or a grade for a specific question in an exam session'). This distinguishes it from sibling tools like 'exams_sessions_saveOverallFeedback' which targets the entire session.

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 providing feedback on individual questions but does not explicitly mention when to use this tool versus alternatives (e.g., 'saveOverallFeedback' or 'editAnswer'). No exclusions or when-not-to-use guidance 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?

No annotations are provided, so the description bears full responsibility. It implies a write operation but does not disclose whether feedback is overwritten, merged, or cleared (despite schema allowing null). Missing details on idempotency, permissions, or side effects like triggering notifications or status changes.

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 waste. However, it is too brief given the missing contextual information (e.g., parameter roles, when to use). Conciseness does not compensate for lack of completeness.

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, no annotations, and only 3 parameters with minimal schema coverage. The description fails to explain return values, error states, or prerequisites (e.g., session must exist, feedback must not be generated already). Incomplete for a mutation 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?

Only 33% of parameters have descriptions in the schema (feedback). The description adds no new meaning beyond the schema: id and sessionId are unexplained, and the feedback parameter description in the schema already states 'Teacher feedback for the test as a whole'. The null option is not clarified.

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 ('Set teacher feedback for the test as a whole') and the resource ('exam session'). It distinguishes from sibling tools like exams_sessions_generateOverallFeedback (generation vs manual setting) and exams_sessions_saveFeedback (per-question vs overall).

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 on when to use this tool versus alternatives (e.g., generateOverallFeedback, saveFeedback). No mention of prerequisites, such as whether feedback must be generated first or whether the session must be in a specific state.

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 provided, so the description must convey behavior. It fails to disclose whether the operation is idempotent, asynchronous, or modifies state. 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, but it is overly terse for the tool's complexity, sacrificing 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?

With no output schema, no annotations, and minimal parameter info, the description should provide context on return values, side effects, and prerequisites. It provides none.

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?

Input schema has one required 'id' parameter with 0% description coverage. The description does not explain what 'id' refers to (e.g., exam session ID, document ID), leaving the agent to guess.

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 'Scan student answers from a document.' which indicates the action and resource, but the verb 'scan' is ambiguous (optical vs. digital) and the description does not distinguish this from sibling tool 'exams_sessions_scanDocument'.

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 on when to use this tool versus alternatives. With a similarly named sibling, explicit usage context is needed but absent.

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?

The description mentions 'background task' implying asynchrony, but does not explain how to monitor progress or retrieve results. No annotations are provided, so the description should disclose behavioral traits like mutability, side effects, or required permissions. It does not.

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 without waste, but it is too concise and lacks essential details, making it less helpful.

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 output schema, no annotations, and no parameter explanations, the description is incomplete. The agent cannot fully understand how to use the tool or what to expect.

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 0%, and the description fails to explain the meaning or purpose of the 'id' and 'documentUrl' parameters. The agent has to infer from context, which is insufficient.

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 (start background task) and the resource (extract student answers from PDF). However, it does not differentiate from the sibling tool exams_sessions_scan, which may perform a similar function.

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 on when to use this tool vs alternatives. No context about prerequisites or integration with other tools.

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 should disclose behavioral traits. It mentions 'initiate a job' implying asynchronicity, but lacks details on side effects, permissions, or how to track progress.

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?

One concise sentence that directly states the action and key inputs. No unnecessary words, though it could be slightly more 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?

Given the tool's complexity (job initiation, AI generation) and lack of output schema, the description should explain return value, job tracking, or next steps. 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?

The only parameter 'id' is not described at all, despite 0% schema description coverage. The description fails to explain what 'id' refers to or how it relates to generation.

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 it initiates a job to generate exam questions using AI, based on specified source materials and metadata. However, it does not distinguish itself from similar siblings like 'exams_questions_generate'.

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 on when to use this tool versus alternatives, no prerequisites or context provided. The description is purely declarative.

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 must fully disclose behavioral traits. It only states 'Update an existing exam,' implying a mutation, but fails to indicate if the update is partial or full, what happens on error, or whether it requires specific permissions. This is insufficient for safe invocation.

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 but lacks substance. While it avoids verbosity, it does not add value beyond the tool's name. It is minimal but not tautological, earning a mid-range 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?

Given no output schema, no annotations, and minimal input description, the description fails to provide complete context for a mutation tool. It does not address return values, error scenarios, or the scope of updates, making it inadequate for correct usage.

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 0% description coverage for its single parameter 'id', and the description does not mention or explain this parameter. The description 'Update an existing exam' does not clarify that the exam ID is required or how to supply updated fields, leaving the agent without essential usage details.

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 'Update' and the resource 'exam', making the tool's purpose unambiguous. However, it does not differentiate from sibling tools beyond the name, which is acceptable since 'exams_update' is the only update tool for exams. The lack of detail on what fields can be updated slightly reduces clarity.

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 exams_create or exams_delete. There is no mention of prerequisites (e.g., exam must exist) or context such as typical workflows, leaving the agent without sufficient decision-making information.

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 present, and the description only indicates a write operation without disclosing effects, permissions needed, or any side effects. It fails to add behavioral context beyond the verb 'create'.

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, but it lacks structure such as separating purpose from usage. It is appropriately short for a simple tool but could benefit from more detail without being verbose.

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 output schema and minimal annotations, the description should compensate but only states the basic action. It omits important details like behavior when 'name' is omitted, potential errors, or return value.

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 0% description coverage, and the tool description does not explain the 'name' parameter beyond what the schema provides (a string with length constraints). No additional meaning or constraints are given.

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 (folder) with scope ('in the current workspace'). It distinguishes from sibling tools like folders_delete and folders_list which handle different operations.

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 when to create vs. update a folder. No prerequisites or conditions 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?

The description discloses a key behavioral trait: if there are exams in the folder, they will be moved out. However, it does not mention irreversibility, required permissions, or other potential side effects. With no annotations, more detail would improve 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?

Two sentences front-load the primary action ('Delete a folder'), with no wasted words. Every sentence adds value, especially the behavior of moving exams.

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 covers the main effect and a notable side effect. However, it lacks information about return values, error cases, or prerequisites. Given the tool's simplicity, it is minimally complete but has 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?

The schema has one required parameter 'id' with no description (0% coverage). The description does not explain the parameter beyond implying it's the folder ID. It provides no additional meaning or constraints.

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 a folder' and specifies the resource is from the current workspace. It distinguishes from sibling tools like folders_create, folders_list, and folders_update by being the delete operation, and adds a unique detail about moving exams out.

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 is clear about when to use it (to delete a folder). There are no explicit alternatives or when-not-to-use scenarios, but the context of sibling tools makes it obvious. For a simple delete, this is adequate.

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?

The description indicates a read-only, non-destructive operation ('Get a list'). With no annotations, it adds sufficient behavioral context. No contradictions.

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 verb and resource, no redundant words. 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 zero-parameter, no-output-schema tool, the description fully covers what the tool does: listing folders for exam organisation in the current workspace.

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?

No parameters exist, so schema coverage is 100%. Description adds no parameter info, but baseline for 0 parameters is 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 clearly states the verb 'Get' and resource 'folders', specifies scope 'within the current workspace' and purpose 'for exam organisation', distinguishing it from sibling tools like folders_create or folders_delete.

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 like folders_list, or when not to use it. However, for a simple list operation, the usage context is 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, the description must carry the burden of behavioral disclosure. It only says 'Update', which implies mutation, but no details on side effects, reversibility, or required authorization.

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, but it is overly minimal. It could include parameter details without becoming verbose.

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 no output schema and no annotations, the description fails to provide sufficient context. It omits return value, prerequisites, and any behavioral traits beyond the basic action.

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 0%, and the description does not explain the 'id' (required) or 'name' (optional with constraints) parameters. The parameters are completely undocumented 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 'Update', the resource 'folder', and importantly specifies 'existing in the current workspace', distinguishing it from sibling tools like folders_create, folders_delete, and folders_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?

No guidance is provided on when to use this tool versus alternatives, nor any preconditions like folder ownership or permissions. The description is purely declarative.

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 present, and the description only says 'Get a list of rubrics that exist within the current workspace.' It fails to disclose any behavioral traits such as pagination, ordering, or permission 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?

Single sentence with no wasted words, perfectly concise for a 0-parameter 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 too brief; it lacks output format details, pagination information, and does not set expectations for the returned list. Given no output schema and no annotations, more 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 no parameters (0), and schema description coverage is 100%. Baseline of 4 applies as the description need not add parameter info.

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 'Get' and the resource 'rubrics', and distinguishes from sibling tools like postRubrics (create) and deleteRubricsid (delete).

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 on when to use this tool versus alternatives (e.g., attributes_list for other lists). No exclusions or context 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 must fully disclose behavioral traits. It only mentions the action and role requirement, omitting details such as idempotency, behavior if the member already exists, or any side effects. This is insufficient 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, efficient sentence that conveys purpose and permission requirements without any extraneous 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 two complex request body alternatives (by actor or email) and no output schema. The description does not explain these alternatives nor any return values, making it incomplete for effective 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?

The input schema has two parameters: 'id' (described as 'Group ID') and 'body' (undescribed, with two alternative formats). Schema description coverage is 50%, and the description adds no extra parameter details. The agent must rely solely on the schema, which lacks documentation for the 'body' parameter.

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: 'Add a member to a group.' It distinguishes from sibling tools like 'groups_removeMember' and 'groups_updateMember' by focusing on the addition 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 description specifies the required roles: 'Requires group manager/owner role or org admin/owner.' This provides clear context on when the tool can be used, though it does not explicitly mention when not to use it or list 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 must disclose behavioral traits. It mentions the role requirement but fails to address potential conflicts (e.g., duplicate group names) or the result of creation (e.g., no response details).

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, using two short sentences with no superfluous words. It is front-loaded with the main 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 the tool's simplicity (one parameter, no output schema), the description is somewhat complete but lacks details on parameter semantics and what the tool returns after creation, which would be expected for a creation action.

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 0%, so the description should compensate by explaining the 'name' parameter. It does not reference the parameter at all, leaving its meaning implied by the parameter name alone.

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 new group', providing a specific verb and resource. It implicitly distinguishes from siblings like groups_delete and groups_list by focusing on creation.

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 specifies a prerequisite role ('Requires admin or owner org role'), guiding when to use the tool. However, it does not explicitly mention when not to use it or compare to alternative tools.

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 states the action (delete) and the side effect (revoke all associated permissions), which is clear and transparent 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?

Two sentences: first states action and side effect, second states required role. Front-loaded, no wasted words, efficient.

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 delete tool with one parameter and no output schema, the description provides all necessary context: what it does, side effect, and authorization 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?

Input schema coverage is 100% with a single parameter 'id' described as 'Group ID'. The description does not add any additional meaning beyond what the schema provides, so a 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 clearly states 'Delete a group and revoke all associated permissions,' using a specific verb and resource. It distinguishes itself from sibling tools like groups_create, groups_update, and groups_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 specifies the required roles: 'Requires group manager/owner role or org admin/owner.' This provides clear context for who can use the tool, but does not explicitly mention when not to use it 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?

Despite no annotations, the description discloses an important behavioral nuance: that when restricted group visibility is enabled, the tool only returns groups the user belongs to. This adds transparency beyond the function 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 extremely concise: two short sentences with no excess verbiage. The purpose is front-loaded, and every word adds 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?

The description covers the essential purpose and a key condition. It is complete for a simple list tool with no parameters, though it could optionally mention output format or ordering.

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?

There are no parameters, so the baseline is 4. The description adds context by explaining what the tool returns and the visibility condition, which goes beyond the empty 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 action 'list all groups' and the resource 'groups in the organization'. It distinguishes from sibling tools like groups_listMembers which list members of a group, 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?

The description provides conditional guidance on when results may be limited (restricted visibility). While it doesn't explicitly exclude alternatives, the context implies it is the primary list tool for groups, and the guidance is helpful for understanding output variations.

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 description carries full burden. It reveals that user info is resolved and visibility restrictions are respected, which adds behavioral context beyond the schema. However, it omits details on read-only nature, pagination, or performance traits.

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 concise sentences, front-loaded with the primary purpose, and every word adds value. Zero wasted content.

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 simple tool with one parameter and no output schema, the description covers core functionality and visibility considerations. However, details about return format, pagination, or member ordering are missing, which would aid 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?

Schema coverage is 100% and the description does not add extra meaning to the single parameter 'id' beyond what the schema provides ('Group ID'). 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 clearly uses the verb 'list' and the resource 'members of a group' with additional detail 'with resolved user info' and 'respects restricted group visibility'. It distinguishes itself from sibling tools like groups_addMember, groups_removeMember, and groups_list by specifying membership retrieval.

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 listing group members but does not explicitly state when to use this tool over alternatives like groups_list (which lists groups) or groups_addMember. No context on prerequisites or when not to use 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?

No annotations are provided, so the description must disclose behavioral traits. It adds role requirements and the owner restriction, but does not mention side effects, reversibility, or error conditions. This is minimal for a destructive 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 two sentences, straightforward, and contains no unnecessary words. It front-loads the action and then adds role and constraint details.

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 tool with no output schema, the description covers purpose, requirements, and a constraint. However, it lacks details on outcome, error handling, or idempotency, which would be helpful for an 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% with descriptions for both parameters ('Group ID', 'User ID of the member'). The description does not add any extra meaning 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 clearly states the action 'Remove a member from the group', with the verb 'remove' and the resource 'member from group'. It distinguishes from sibling tools like groups_addMember and groups_updateMember.

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 specifies required roles ('group manager/owner role or org admin/owner') and a key constraint ('Cannot remove the owner'). While it does not explicitly compare to alternatives, the usage context is clear.

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?

Without annotations, the description carries full burden. It discloses role requirements, but omits other behavioral traits such as potential side effects (e.g., breaking references), whether the operation is reversible, or what the response looks like.

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, no fluff. Every sentence adds 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?

Despite being a simple tool, it lacks critical context: no output schema, no mention of response, and ambiguity about the optional name parameter (if omitted, does it rename?).

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 only 50% (id has a brief description, name has none). The description does not add meaning to the name parameter, such as its optionality or constraints.

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: 'Rename a group'. This specific verb-resource pair distinguishes it from siblings like groups_updateMember (which updates membership) and groups_create.

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 usage context by specifying required roles ('group manager/owner role or org admin/owner'), but does not explicitly state when not to use this tool or compare it to 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 the full burden. It reveals the permission requirement, which is a key behavioral trait. However, it does not disclose potential side effects, idempotency, or error states, which would be beneficial 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 concise—two sentences, front-loaded, with no extraneous information. Every sentence 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?

For a simple mutation with three parameters and no output schema, the description adequately covers purpose and prerequisites. However, it could mention the expected response (e.g., success/failure) for full 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?

Schema coverage is 67%, meaning two parameters (id, userId) have descriptions, and role has an enum. The description adds no extra information beyond the schema. Given moderate coverage, 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 clearly states 'Change a member's role in the group', which is a specific verb (change) and resource (member's role in the group). This distinguishes it from sibling tools like groups_addMember, groups_removeMember, and groups_listMembers.

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 specifies the required roles: 'Requires group manager/owner role or org admin/owner.' This provides clear context on who can use the tool, though it does not explicitly state when not to use it (e.g., for adding/removing members).

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?

The description does not disclose any behavioral traits beyond the basic action. With no annotations, it fails to explain side effects, reversibility, or what happens to the job after cancellation. The agent gets minimal 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 extremely short (one sentence) but lacks necessary information. Conciseness should not sacrifice completeness; here it is under-specified.

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 no annotations, no output schema, and a single parameter, the description should provide comprehensive context (e.g., success/error responses, idempotency, concurrency). It fails to do so, leaving the agent with inadequate information.

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 only parameter 'id' is not described beyond the schema. With 0% schema coverage, the description should clarify what 'id' refers to (e.g., job ID, task ID) but does not, adding no value over the schema itself.

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 the verb 'cancel' and the resource 'background job', which clearly indicates the tool's function. However, it lacks detail to differentiate from other cancellation tools like exams_cancelGeneration, though the context of 'background jobs' makes it distinct.

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 jobs_get or other cancel tools. There is no mention of prerequisites, conditions, or context for cancellation.

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 behavioral details, but it only says 'poll the status'. It does not explain what the returned status looks like, whether the tool is idempotent, error conditions, or any rate limiting. The agent lacks sufficient information about the tool'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 a single short sentence, which is concise but too minimal. It lacks essential information, making it under-specified rather than efficiently concise. A well-structured description would front-load the purpose and then add necessary details.

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 no output schema, no parameter descriptions, and no annotations, the description should be more complete. It provides only the basic purpose, omitting details about return values, possible errors, and usage context. For a polling tool, this is insufficient.

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 one required parameter 'id' with no description (0% coverage). The description does not add any meaning to this parameter; it simply repeats the parameter name. The agent cannot infer what 'id' refers to or its format.

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 'poll' and clearly identifies the resource as 'the status of a background job'. It distinguishes from sibling tools like jobs_cancel, which is about canceling jobs, thus making the tool's 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 guidance is provided on when to use this tool versus alternatives (e.g., when to poll a job rather than cancel it). There is no mention of prerequisites (e.g., job must exist) or context for polling frequency.

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?

The description discloses the output (signed and public URLs) but lacks behavioral details such as authentication requirements, URL expiration, or that the actual file upload is separate. With no annotations, the description carries the full burden, which 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?

The description is a single, concise sentence that communicates the core function without extraneous information. Every word earns its place, making it highly efficient.

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 good schema coverage and an output schema (not described), the description omits critical context: it does not explain that the signed URL is used for subsequent uploads, mention URL expiration, or provide usage context among many sibling tools. The tool's simplicity does not excuse the lack of behavioral and practical details.

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, with defaults and descriptions for all three parameters (filename, type, contentType). The description adds no additional meaning beyond the schema, so a 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 clearly states the tool returns a signed URL for uploading and a public URL for access, specifying the verb 'returns' and resource 'URLs for file'. The name 'media_upload' reinforces the purpose. However, it does not explicitly differentiate from potential sibling upload tools, though siblings are unrelated.

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. There is no mention of prerequisites, context, or exclusion cases, leaving the agent to infer usage from the tool 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 provided, and description only states a read operation. Does not disclose authentication requirements, rate limits, or any side effects. Minimal 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?

Single sentence that is clear and to the point. No superfluous words. Perfectly 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?

Given no output schema and no annotations, the description lacks details about returned data or limitations. For a tool with many siblings, more context on scope and output would be helpful.

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?

Input schema has zero parameters with 100% coverage, so baseline is 4. Description adds no additional parameter info, but none is needed.

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 clearly states the verb 'Get' and the resource 'current user's account details', making it specific and distinct from siblings like me_update or users_get.

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 on when to use this tool versus alternatives (e.g., me_update for modifications or users_get for other users). Does not mention prerequisites or 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?

With no annotations, the description must disclose behavioral traits. It only states 'Update', implying a write operation, but omits details like required permissions, immediacy of effects, or any side effects. This is insufficient for safe invocation.

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 sentence is concise and front-loaded with the action and resource. While minimal, it avoids unnecessary words, earning a high conciseness score. Some structure improvement could include separating purpose and behavior.

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 lacks information about return values (whether the updated account is returned) and any behavioral context. For a mutation tool with no output schema, this omission makes the description incomplete for an agent to anticipate outcomes.

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 description adds no new meaning beyond the schema's description of name and preferences. The tool is simple, and the description does not elaborate on parameter constraints or usage, resulting in a baseline score.

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 verb 'Update' and the resource 'current user's account details', clearly distinguishing it from reading tools like me_get. However, it could be more specific about the scope of updates beyond name and preferences, though the schema fills this gap.

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 description does not indicate when to use this tool versus alternatives such as me_get for reading or users_update for updating other users, leaving the agent without context for 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?

No annotations are provided, so the description must carry behavioral disclosure. While 'Get' implies read-only, it does not mention authentication needs, rate limits, or what happens if configuration is missing.

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?

Extremely concise at four words, front-loaded with no extraneous 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?

For a simple getter with no parameters and no output schema, the description adequately conveys the purpose. It could mention return value nature, but not 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?

No parameters exist, so schema coverage is 100% trivially. Baseline 4 is appropriate as the description adds no parameter details.

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 'Get custom domain configuration' clearly specifies the verb and resource, distinguishing it from sibling tools like org_customDomain_update.

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 on when to use this tool versus alternatives. The description does not mention context 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 must disclose behavioral traits. However, it only states 'Update' without explaining mutation implications, permissions, reversibility, or side effects. The description fails to compensate for the lack of 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?

The description is concise at just four words, but it lacks structure and depth. While it is not verbose, the extreme brevity sacrifices clarity and completeness. A bit more detail would be warranted.

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 no output schema, no annotations, and a single undocumented parameter, the description is incomplete. It does not explain return values, side effects, or success criteria, leaving the agent with insufficient information 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?

The input schema has one parameter with 0% description coverage, and the description does not add any meaning beyond 'custom domain configuration'. It does not explain what 'customDomain' values are acceptable or how to use the null type. The description should clarify the parameter's role.

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 'Update custom domain configuration' clearly states the action (update) and the resource (custom domain configuration), and it distinguishes itself from the sibling tool 'org_customDomain_get' which retrieves the configuration.

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. There is no mention of prerequisites, conditions, or when not to use it, leaving the agent without context for appropriate invocation.

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 only says 'Delete', implying a destructive action, but does not explain consequences (e.g., irreversible, cascading deletes, required permissions). This is insufficient 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 extremely concise at two words. It is front-loaded and to the point, though it may be under-specified for a delete action. It earns its place with no extra content.

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 performs a notable delete operation with no parameters or output schema, the description is incomplete. It fails to clarify which organization is deleted, return behavior, or side effects. More detail is essential for safe usage.

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 zero parameters, and schema description coverage is 100% (none to describe). Per guidelines, 0 parameters yields a baseline of 4. The description adds no parameter info, but none is needed as there are no 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 'Delete organization' clearly states the verb and resource, matching the tool name. It distinguishes from sibling tools as no other tool performs org deletion, but lacks specificity about which organization is targeted (e.g., current org vs. by ID), which is ambiguous given zero parameters.

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, or any prerequisites like admin rights. The description does not mention context or exclusions, leaving the agent to infer 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?

No annotations provided. Description implies read-only operation, but no confirmation of safety, auth requirements, or side effects. Does not disclose what data is returned.

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?

Extremely concise at two words, but lacks critical details. Conciseness should not come at the expense of 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?

Given no output schema and no parameters, the description fails to explain what the tool returns or how to interpret the result. Insufficient for a standalone 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?

Input schema has no parameters with 100% coverage, so description adds no value beyond schema. Baseline of 3 is appropriate as schema already fully documents 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?

Description states verb 'Get' and resource 'organization', which is clear but ambiguous given sibling tools like 'orgs_list' and 'org_customDomain_get'. Does not specify which organization (e.g., current context or by ID).

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 on when to use this tool versus alternatives such as 'orgs_list' or 'org_customDomain_get'. No context about prerequisites or scope.

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 present, the description must fully disclose behavioral traits. It only states the action 'Create' without mentioning side effects, permissions, return values, or idempotency. This leaves significant gaps.

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 concise (one sentence) and front-loaded, but it omits valuable details that could make it more helpful without adding much length.

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 lack of output schema and annotations, the description is insufficient. It does not explain what the tool returns or how to handle the response, which is critical for an agent to use 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?

The input schema has 0% coverage, and the description does not explain the 'name' parameter (e.g., format, uniqueness, default behavior). It should compensate for the lack of schema descriptions but fails to do so.

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 'Create', the resource 'new workspace', and the purpose 'to collaborate with others on exams'. It is easily distinguishable from sibling tools like orgs_list, org_get, org_update, and org_delete.

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