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

Annotations already indicate a non-read-only (write) operation and non-destructive behavior. The description adds that it modifies a contact by adding tags, which is consistent. It does not detail idempotency or what happens if a tag already exists, but overall behavior is clear.

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 only two sentences with no extraneous words. It front-loads the purpose and follows with pragmatic guidance. However, it could be more precise about parameter formats without adding 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 zero schema descriptions and a write operation, the description covers the workflow (list_contacts, list_tags) and basic purpose. However, it omits key details like whether multiple tags can be added in one call (implied by array) and the exact format expected for tag_names. Output schema exists, so return values are less critical, but missing parameter behavior reduces completeness.

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

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

The schema has 0% description coverage, so the description must clarify parameter meaning. It mentions 'contact ID' for uuid and 'tags IDs or names' for tag_names, but ambiguously: does tag_names accept IDs, names, or both? The parameter is named 'tag_names' implying names, yet the text says 'IDs or names,' causing confusion. This adds limited clarity.

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 'Add tags to a single contact,' specifying the verb and resource. It distinguishes from sibling remove_tags by the action 'add' vs 'remove.' The purpose is instantly understood.

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 explicit prerequisites: 'Use list_contacts first to find the contact ID' and 'Use list_tags to find tags IDs or names.' This guides the workflow but does not explicitly exclude alternatives or contrast with sibling tools beyond the 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?

Annotations indicate readOnlyHint=false and destructiveHint=false, which is consistent with creation behavior. The description adds transparency by specifying that 'fields' is a JSON object and directing to list_fields for available keys. This goes beyond the annotation by detailing parameter usage.

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: three sentences that pack essential information. No filler or unnecessary details. Each sentence serves a purpose (action, parameter guidance, prerequisite).

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 and 1 required, the description explains only the custom fields parameter and its prerequisite. With an output schema present, return values need no explanation. However, the purpose and behavior of other parameters (e.g., validation, defaults) are omitted, leaving the description slightly incomplete for a creation tool.

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

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

Schema description coverage is 0%, meaning no parameter descriptions in the schema. The description only explains the 'fields' parameter fully, leaving name, ddi, phone, email, and username undocumented. While the 'fields' guidance is helpful, the majority of parameters lack semantic context, necessitating higher compensation.

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 'Creates a contact' with a clear verb and resource. While it doesn't explicitly differentiate from sibling tools like create_deal or create_tag, the context of sibling names and the action itself make it clear. A more explicit statement of what constitutes a 'contact' might elevate to 5.

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 includes a key guideline: 'Call list_fields first to discover available field keys.' This provides a clear prerequisite when using the 'fields' parameter. However, it doesn't mention when to use this tool versus alternatives like update_contact, but that omission is minor.

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

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

Annotations already indicate readOnlyHint=false (mutation) and destructiveHint=false. The description adds that it creates a new deal, which is consistent but adds no additional behavioral traits like side effects, rate limits, or error conditions beyond 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 three succinct sentences with no wasted words. It front-loads the main purpose and provides essential usage guidance efficiently.

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

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

Despite the complexity of 10 parameters and zero schema coverage, the description only covers 2 parameters (origin_id and fields). It omits mention of other optional parameters like stage_id, user_id, etc., leaving the agent underinformed. An output schema exists, which explains return values, but parameter coverage 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 description explains origin_id (required) and fields (custom JSON object), but ignores 8 other parameters (name, phone, email, etc.). With 0% schema description coverage, the description should compensate by covering more parameters, but it does not. This leaves many parameters undocumented.

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 deal in the CRM,' which is a specific verb and resource. It distinguishes from sibling create tools like create_contact by explicitly naming the resource. It also provides context about required origin_id and custom fields.

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 advises using list_origins to find valid origin IDs and list_fields to discover field keys, offering clear prerequisites. However, it does not explicitly state when not to use this tool versus alternatives like update_deal, but the context is sufficient for a create operation.

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

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

Annotations already indicate non-read-only and non-destructive. The description adds the constraint of available colors, which is useful behavioral context. However, no mention of permissions, idempotency, 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?

Two concise sentences: first states purpose, second lists valid color values. 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?

Given an output schema exists, description need not detail return values. It covers the primary action and a key constraint, though omits potential duplication or side-effect 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?

Schema has 0% description coverage. Description only defines the color parameter's allowed values, but the name parameter remains undocumented beyond type and requirement.

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 'Create a new tag' clearly states the action and resource. While it does not explicitly differentiate from siblings, the verb implies creation, distinguishing it from 'add_tags' (likely adding existing tags) and 'delete_tag'.

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 mention of prerequisites, context, or when not to 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?

Annotations already mark destructiveHint=true. The description adds a warning and a permission guideline, providing context beyond annotations. It explains what the tool does (delete) and the need for user approval.

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?

Three concise sentences: warning, action, prerequisite. No unnecessary words. Information is 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 tool's simplicity (one param, no nested objects), the description covers purpose, usage, and behavior. Output schema exists, so return values are handled. No 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 schem has one required param 'uuid' with string type, no description. The description mentions 'by its ID' but doesn't explicitly map to the uuid parameter. However, the param name is self-explanatory, so the description adds minimal value. Baseline 3 due to schema having 0% coverage, but single param clarity keeps it adequate.

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

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

The description clearly states 'Deletes a contact by its ID.' The verb (delete) and resource (contact) are explicit. It distinguishes from siblings like update_contact or list_contacts by specifying the action is deletion.

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 advises 'Use list_contacts first to find the contact ID,' providing a clear prerequisite. It also instructs to ask user permission due to destructive nature. It does not explicitly state when not to use, but the warning implies caution.

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

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

Annotations already set destructiveHint=true and readOnlyHint=false. Description reinforces the destructive nature with a warning and permission requirement, adding necessary context beyond 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?

Two sentences plus a warning; each sentence serves a purpose: alerting about destructiveness, describing action, and providing guidance. No redundancy.

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

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

For a simple one-parameter delete tool, the description covers key aspects: destructive action, permission requirement, and ID retrieval method. Output schema exists (not shown) but doesn't need explanation. Slight gap in parameter 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?

Only parameter is 'id' with 0% schema coverage. Description mentions 'by ID' but does not clarify format, source, or constraints. Schema coverage is low, and description fails to compensate meaningfully.

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

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

Description clearly states 'Remove a single tag by ID,' specifying the action and resource. It distinguishes from sibling tools like 'remove_tags' which handles multiple tags.

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

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

Provides explicit guidance to 'Use list_tags to find the tag ID' and warns about destructive action, asking for user permission. Could mention when not to use (e.g., for batch removal use remove_tags).

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. Description adds 'full details' and 'by UUID' but does not disclose any other behavioral traits. No contradiction.

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

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

Two sentences, no redundancy, front-loaded with key verb and resource. Every word earns its place.

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

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

Tool is simple with one parameter, output schema exists, and the description covers the prerequisite workflow. No gaps given the context signals.

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%, but the description mentions the parameter (uuid) with context ('by UUID'). Given only one simple parameter, the description provides sufficient additional meaning over the schema 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?

Clearly states the action (Get), resource (full details of a single contact), and identifier (by UUID). Differentiates from list_contacts and other sibling tools.

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

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

Explicitly advises to use list_contacts first to find the contact ID, providing clear context for use. Does not mention when not to use or alternative tools, but the guidance is helpful.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds no further behavioral context, such as error handling or authentication 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?

Two sentences, front-loaded with the core purpose. Every sentence is essential and 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 tool's low complexity, presence of annotations, and an output schema, the description adequately covers how to use it and where to get the required 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?

Schema coverage is 0% for the only parameter 'id', but the description implies it is the deal identifier. No additional details on format or constraints are provided.

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

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

The description 'Retrieve a single deal by ID' uses a specific verb and resource, clearly distinguishing it from sibling tools like list_deals.

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 instruction 'Use list_deals to find the deal ID' provides explicit context for when to use this tool, though it does not state when not to use 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's simple 'Retrieve' is consistent but adds no extra detail. With annotations covering safety, the description meets the minimum bar.

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

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

Two sentences, no wasted words. The first sentence states the action and resource, the second provides a prerequisite. 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?

For a simple get-by-ID tool with only one parameter and an output schema, the description covers the essential purpose and prerequisite. It could mention the return type, but the output schema makes that unnecessary.

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 format or expected value of the ID parameter, only indirectly suggests using list_groups to find it. This is insufficient compensation for the missing 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 clearly states 'Retrieve a single group by ID', with a specific verb and resource, and distinguishes from the sibling list_groups tool.

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

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

The description provides guidance on how to find the group ID by referencing list_groups, which is a clear prerequisite. It does not explicitly mention when not to use this tool, but the context is sufficient.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so description adds no extra behavioral context. However, it is a simple retrieval with no side effects, so description is adequate.

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

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

Two sentences, no wasted words, front-loaded with core purpose and usage guidance.

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?

Complete for a single-resource retrieval: parameters are minimal, output schema exists, annotations cover safety, and sibling tools are listed. No 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 description mentions 'by ID' which aligns with the required id parameter, but does not provide additional detail beyond what the parameter name suggests. Schema coverage is 0%, but the parameter is self-explanatory.

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 verb 'Retrieve' and resource 'lost status' with scope 'by ID'. Distinguishes from sibling list_lost_status by directing to it for finding IDs.

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?

Explicitly tells when to use (when you have an ID) and directs to list_lost_status to find the ID, providing clear context and an alternative.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds minimal context beyond the verb 'Retrieve', which aligns with the annotations. No additional behavioral traits (e.g., rate limits) are disclosed.

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

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

The description is very short (one sentence) and front-loads the key information. However, it could be structured more informatively, e.g., by adding bullet points or clarifying the output. It earns its place but lacks depth.

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, read-only, output schema exists), the description is minimally adequate. It does not mention the return format or that the output schema contains details, but the output schema itself covers that. The description could be more helpful with usage 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?

With 0% schema description coverage, the description must compensate. It mentions 'by ID' but does not explain the format or expected value of the 'id' parameter (e.g., UUID, numeric). The description adds little beyond the schema's type declaration.

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 explicitly states the action ('Retrieve'), the resource ('details of a single organization'), and the identifier method ('by ID'). It clearly distinguishes from sibling tools like 'list_contacts' or 'update_organization'.

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., when a list is needed). The description implies that a specific ID is required but gives no context on prerequisites or when not to use 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?

Annotations already provide readOnlyHint=true and destructiveHint=false, so no contradiction. The description adds no additional behavioral details beyond purpose, which is acceptable given the annotations cover safety profile.

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 concise sentences, front-loaded with verb and resource, no wasted words.

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

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

With an output schema present, the return structure is documented. Description covers core purpose and discovery of input. Lacks mention of error handling or edge cases, but still adequate for a simple retrieval tool.

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

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

Schema description coverage is 0%, and the description only says 'by ID'—minimal additional meaning beyond the parameter name. No format or constraints explained.

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

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

The description clearly states the action ('Retrieve a single origin by ID') and the resource, distinguishing it from siblings like list_origins which is mentioned as a means to find the 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?

Explicitly tells users to use list_origins to find the origin ID, providing clear guidance on prerequisite step. Does not explicitly say when not to use, but context implies this tool is for when ID is already known.

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 aligns with readOnlyHint and destructiveHint annotations, adding minimal new information beyond that it retrieves a single item.

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 concise sentences, front-loaded with core purpose, 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?

Given the simple tool (one parameter, output schema present), the description sufficiently covers what it does and how to use it.

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 schema description coverage at 0%, the description adds 'by ID' but does not further clarify that the parameter is the tag's unique identifier.

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

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

The description clearly states the verb 'retrieve' and resource 'single tag by ID', and distinguishes from sibling tools like list_tags and create_tag.

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

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

Provides clear guidance to use list_tags to find the tag ID, helping the agent decide when to use this tool, though does not explicitly mention when not to use 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds no further behavioral details (e.g., rate limits, response format), but is adequate given the 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?

Two sentences, no fluff, front-loaded with the action. 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?

For a simple retrieval tool with one parameter and an output schema, the description provides the necessary context: what it does, how to use it, and a pointer to a sibling for ID lookup.

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 does not add meaning beyond the parameter name 'id' (e.g., what kind of ID, format). The schema coverage is 0%, so the description should compensate, but it only repeats 'by ID'.

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

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

The description clearly states the verb 'Retrieve' and the resource 'a single user by ID', which is specific and distinguishes it from sibling tools like list_users.

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 explicitly tells the user to use list_users to find the ID if they don't have it, providing clear context. However, it does not explicitly mention when not to use this tool versus other get tools, but the resource distinction 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?

Beyond annotations (readOnlyHint, destructiveHint), the description adds essential behavioral details: returns up to 1000 per call, pagination via offset, optional filters, and phone format note. 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?

The description is three sentences, front-loaded with purpose, and every sentence adds value. No redundant or verbose 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 6 optional parameters and an output schema, the description covers purpose, filtering, pagination limit, and pagination method. It is fully complete for agent decision-making.

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 fully explains all 6 parameters: name, email, phone (without country code), tag_names, origin_id, and offset for pagination. This adds significant meaning beyond the bare 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 'List all contacts from the CRM' with a specific verb and resource. It distinguishes from siblings like get_contact (single) and create_contact by focusing on listing multiple with optional filters.

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

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

The description provides clear context for when to use (retrieve multiple contacts with optional filters, pagination) and references list_origins for valid origin IDs. It does not explicitly mention when not to use it or alternatives like get_contact for a single contact, but the sibling tool names make this implicit.

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?

Description adds useful behavioral details beyond annotations: default status, 1000 limit, offset pagination. Consistent with readOnlyHint and no destructive 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?

Four sentences, each with a distinct purpose: general retrieval, filters, defaults, pagination. No wasted words.

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

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

Covers filters, defaults, pagination limitations. No output schema needed since it exists externally. Lacks mention of ordering, but overall complete for a list tool.

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

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

Schema has 0% description coverage, but description explains all major filter categories (date ranges, user_email, phone, email, tag_names, status, stage_id, offset). Some date parameters not individually listed but covered by 'date ranges (ISO 8601)'. Adds significant semantic value.

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 'Retrieve a list of deals' with explicit verb and resource. Distinguishes well from siblings like get_deal (single), create_deal, etc.

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

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

Provides clear context: defaults to status=OPEN, pagination limit, offset usage. Does not explicitly mention when not to use (e.g., for a single deal use get_deal), but context is strong.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description confirms it's a read-only operation with 'Get'. It does not add extra behavioral context beyond the annotations, but also does not contradict them.

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 the purpose, second provides usage guidance. No unnecessary words. Front-loaded and 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?

The tool is simple with no parameters. The description covers purpose and usage. An output schema exists (not shown), so return values are documented elsewhere. Complete for its complexity.

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

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

The tool has no parameters, and schema coverage is 100%. The description does not need to add parameter information. Baseline score of 4 is appropriate for zero-parameter tools.

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 it 'Get all custom fields available in the account.' This is a specific verb and resource. It distinguishes from sibling tools by focusing on fields, and adds context about discovering field names for contacts and deals.

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 explicitly says 'Use this to discover field names before creating or updating contacts and deals.' This provides clear guidance on when to use it. While there is no explicit when-not, the simple nature of the tool makes it sufficient.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to cover those. It adds value by disclosing the 1000-per-call limit and pagination requirement, which are behavioral traits beyond 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 two sentences with no wasted words. The purpose is stated first (front-loaded), followed by essential pagination details. Every sentence earns its place.

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

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

Given the presence of an output schema, the description does not need to explain return values. It covers pagination limit and offset usage. However, it could mention that groups are different from other entities (e.g., contacts), but that is implied by the tool name and siblings. Overall, sufficient 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 0% description coverage, leaving the single 'offset' parameter undocumented. The description compensates by explaining its purpose ('Use offset to paginate') and providing a concrete example ('offset=1000 for next batch'), adding crucial semantic 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 'Retrieve a list of all groups', specifying the verb (Retrieve) and resource (groups). This distinguishes it from sibling list tools (e.g., list_contacts, list_deals) which target different resources.

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

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

The description provides pagination guidance ('Returns up to 1000 per call. Use offset to paginate'), which is helpful but does not explicitly state when to use this tool over alternatives or when not to use 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?

Annotations indicate read-only and non-destructive behavior. The description adds valuable detail on pagination and the 1000-item limit, going beyond 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?

Two sentences, no wasted words; purpose is front-loaded followed by essential pagination 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 an output schema exists, the description covers the necessary aspects: purpose, pagination, and limit. No 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?

With 0% schema description coverage, the description fully explains the offset parameter's purpose and usage with a concrete example, adding 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 uses the verb 'retrieve' and specifies the resource 'all lost status reasons', clearly distinguishing from the sibling get_lost_status which likely returns a single item.

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

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

Provides explicit pagination guidance with limit and offset example, but does not mention when to use this tool over the sibling get_lost_status.

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?

Beyond annotations (readOnlyHint, destructiveHint), the description adds behavioral traits: returns up to 1000 per call and pagination via offset. This provides valuable context for 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?

Two sentences front-loaded with purpose, followed by required parameter and limits. No wasted words, every sentence earns its place.

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

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

Given the simple tool (2 parameters, no nested objects, output schema exists), the description fully covers filtering, required parameter, pagination limits. No 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?

With 0% schema description coverage, the description compensates by explaining group_id is required and offset is for pagination with an example (offset=1000). This adds significant meaning beyond the schema.

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

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

The description clearly states the verb 'Retrieve' and the resource 'list of origins filtered by group'. It is distinct from siblings like list_contacts or list_groups, though it doesn't explicitly differentiate from get_origin.

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 explicitly states that group_id is required and directs the agent to use list_groups to find valid IDs. This provides clear context for when to use the tool and a prerequisite, but lacks when-not scenarios.

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 adds valuable behavioral context beyond annotations: it mentions the 1000-result limit, optional name filtering, and pagination via offset. Annotations already indicate read-only and non-destructive behavior, so the description enriches that with operational details without contradiction.

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 three concise sentences: the first states the core purpose, the second adds optional filtering, and the third explains pagination. No redundant or unnecessary information; every sentence earns its place.

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

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

Given the existence of an output schema (which documents return values), the description covers all necessary aspects: purpose, filtering, pagination, and result limit. For a simple list tool with two parameters, this is 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?

With schema description coverage at 0%, the description must compensate. It explains the 'name' parameter for filtering and implicitly explains 'offset' through the pagination example. However, it does not specify the matching behavior of the name filter (e.g., exact or partial) or the default value behavior. Still, it provides adequate functional meaning for both parameters.

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

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

The description clearly states the verb 'Retrieve' and resource 'list of tags', with optional filtering by name. It distinguishes from sibling tools like get_tag (single tag) and add_tags (add operation). The purpose is specific and 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 explains when to use filtering and pagination (using offset for batches of up to 1000). However, it does not explicitly contrast with get_tag (single tag retrieval) or specify when not to use the tool. The guidance is clear but lacks explicit exclusions 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the 1000-item limit and pagination behavior, which are critical for agent planning.

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 concise sentences, front-loaded with the core purpose, followed by essential pagination details. No wasted words.

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

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

Given the output schema exists (covering return values) and the tool is a straightforward read-only list operation, the description fully covers usage, limits, and pagination. No gaps for this complexity level.

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 'offset' has 0% schema description coverage, but the description explains its purpose (pagination) with a concrete example, adding value beyond the schema's type/default.

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?

Explicitly states 'Retrieve a list of all users' – a specific verb and resource. This clearly distinguishes from siblings like 'get_user' (single user) and 'list_contacts' (different resource).

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

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

Provides clear pagination guidance: maximum 1000 per call and how to use offset for subsequent batches. Lacks explicit when-not-to-use or alternatives, but the pagination info is highly actionable for correct 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?

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds context that the action is permanent, reinforcing the destructive nature. No contradiction with 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?

Two concise sentences with the warning upfront. Every word is useful and efficient. No unnecessary 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 the presence of an output schema (not shown), the description adequately covers the destructive nature and how to obtain the required ID. Sibling tools exist but are not compared, though the context is sufficient for a simple deletion tool.

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

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

Schema description coverage is 0%, and the parameter 'id' has no description. The description only mentions 'by ID', which is minimal and adds little beyond the schema. For a single parameter with no schema description, more detail (type, format, example) would be valuable.

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 action ('Remove a deal permanently by ID') with a specific verb and resource. However, it does not differentiate from sibling delete tools like delete_contact or delete_tag, which have similar purposes.

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?

Description explicitly advises asking user permission due to destructiveness and suggests using list_deals or get_deal to find the ID. This provides clear context for appropriate use but does not specify 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?

Warns about destructive action and asks for user permission, adding context beyond the destructiveHint annotation. 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?

Three short sentences, each necessary. Warning is front-loaded. No wasted words.

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

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

Covers the key usage flow and safety concern. Output schema exists, so return value detail is not required. Slight lack of edge case handling but sufficient for the tool.

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

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

Schema description coverage is 0%, but the description provides practical guidance on obtaining values (use list_contacts, list_tags). However, it does not explain parameter formats 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 explicitly states 'Remove a tag from a single contact.' using a specific verb and resource. It clearly distinguishes from sibling tools like add_tags and delete_tag.

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?

Includes a warning for destructive action and instructs to use list_contacts and list_tags first for prerequisites. Lacks explicit alternatives but 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?

Annotations already indicate destructiveHint=true, so the update is mutating. The description adds 'Update' which is consistent but does not disclose any additional behavioral traits such as partial update behavior, validation errors, or side effects. With annotations covering the main safety profile, the description adds minimal extra 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 four sentences, front-loaded with the main purpose, then prerequisites, then fields explanation. Every sentence adds value without redundancy. No unnecessary detail 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 presence of an output schema, return values need not be explained. The description covers the core operation, prerequisites, and the important fields parameter. It misses possible details about how optional parameters behave (e.g., whether omitted fields are left unchanged), but overall it is fairly complete for a mutation tool with good annotations.

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 compensate. It explains the 'fields' parameter as a JSON object with an example, but does not explain other parameters (name, ddi, phone, email, username) beyond their names. This provides some added value but lacks detail for the majority of parameters.

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

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

The description clearly states 'Update contact by its ID' with a specific verb and resource. It distinguishes from sibling tools like create_contact, delete_contact, and get_contact by focusing on updating an existing contact identified by UUID. The additional guidance on the fields parameter reinforces the purpose.

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

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

The description provides explicit prerequisites: 'Use list_contacts first to find the contact ID' and 'Call list_fields first to discover available field keys.' This guides when to use the tool. It does not explicitly state when not to use it or compare to alternatives, but the 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?

Annotations already indicate mutation (readOnlyHint=false, destructiveHint=true). The description adds helpful context like status options and fields usage, but does not elaborate on update behavior (e.g., partial vs full overwrite).

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 three sentences, each delivering critical information without redundancy. It is front-loaded with the main action and efficiently provides prerequisites and field guidance.

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?

While the description gives key guidance for using the tool and an output schema exists, it lacks details on update semantics (e.g., whether unspecified fields are cleared or retained). For a destructive mutation tool, this gap leaves the agent uncertain about the tool's full 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?

Schema description coverage is 0%, so the description must compensate. It explains id, status, and fields, but omits 7 other parameters (name, phone, email, value, stage_id, user_id, origin_id) which are self-explanatory but not annotated. The description fails to fully cover all parameters.

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

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

The description clearly states 'Update an existing deal' and provides guidance on finding the deal ID, making the purpose unambiguous. It distinguishes itself from sibling tools like create_deal or remove_deal by focusing on modification.

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 explicitly advises using list_deals or get_deal to find the deal ID and list_fields to discover field keys, providing clear prerequisites. However, it does not mention when not to use this tool or suggest alternatives for different tasks.

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

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

Annotations already indicate destructiveHint=true, and the description confirms 'update.' No additional behavioral details (e.g., permissions, side effects) are provided beyond the annotation, but the prerequisite note adds some 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 three concise sentences: first for purpose, second for usage guidance, third for a parameter explanation. No redundancy or wasted words.

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

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

Given an output schema exists and annotations cover destructiveness, the description adds the prerequisite and a parameter note. It is mostly complete, though it could list all updatable fields explicitly.

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 only explains the 'custom_fields' parameter with an example JSON format. The 'id' and 'name' parameters are left to inference, which is acceptable given their simplicity. Partial but helpful.

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 'Update an existing organization,' using a specific verb (update) and resource (organization), and distinguishes from sibling tools like update_contact and update_deal.

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 advises to 'Use get_organization first to check current data,' providing a clear prerequisite and context for proper use, though it does not explicitly list when not to use or alternative tools.

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