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 clearly states what the tool returns ('numbers and percentages, never specific contacts') and what it doesn't return. However, it doesn't mention potential limitations like rate limits, authentication requirements, or error conditions that would be helpful for a tool performing database aggregation operations.

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 perfectly concise and well-structured: three sentences that each earn their place. The first sentence states the core purpose, the second provides concrete examples, and the third gives explicit usage boundaries with the alternative tool. No wasted words, front-loaded with the most important 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 tool with no annotations and no output schema, the description does an excellent job of explaining what the tool does and when to use it. However, it doesn't describe the output format beyond 'numbers and percentages' - no mention of specific return structure, data types, or error responses. Given the complexity of aggregation operations, more output details 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?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any additional parameter semantics beyond what's in the schema descriptions. It mentions 'query' field usage indirectly through examples but doesn't provide additional context about how parameters interact or are processed.

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 purpose: 'Get numerical statistics and counts ONLY' with specific examples like 'how many work at Google?' and 'what % are engineers?'. It explicitly distinguishes from sibling tools by contrasting with 'search endpoint' for 'who' questions or contact details, making the distinction from searchContacts and getContact very clear.

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

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

The description provides explicit guidance on when to use this tool versus alternatives: 'Use search endpoint instead for any "who" questions or to get actual contact details.' It gives clear examples of appropriate use cases (counting questions, percentage queries) and explicitly names the alternative tool (search endpoint/searchContacts).

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 this is a creation operation, implying mutation, but doesn't mention authentication requirements, rate limits, error handling, or what happens on success/failure. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves beyond its basic purpose.

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 perfectly concise with two clear sentences that each earn their place. The first sentence states the core purpose, and the second provides important usage guidance. There's zero wasted language or redundancy, making it easy for an agent to parse quickly.

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 this is a mutation tool with no annotations and no output schema, the description provides adequate basic context about purpose and usage boundaries. However, it lacks information about what happens after creation (return values, success indicators) and doesn't address behavioral aspects like permissions or side effects, which would be important for a creation operation.

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

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

Schema description coverage is 100%, so the schema already documents all 9 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. According to the rules, when schema coverage is high (>80%), the baseline score is 3 even with no param info in the description, which applies here.

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

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

The description clearly states the action ('Create a new contact record') and resource ('in Clay'), making the purpose immediately understandable. It distinguishes this tool from sibling tools like 'createGroup' or 'createNote' by specifying it's for contacts. However, it doesn't explicitly differentiate from 'updateGroup' or other contact-related tools beyond the basic scope.

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

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

The description provides explicit guidance on when to use this tool ('when you need to create a completely new contact') and when not to use it ('not for adding contacts to groups'). This helps the agent avoid misusing it for group operations. However, it doesn't mention alternatives like 'searchContacts' for finding existing contacts or clarify relationships with other contact 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. It discloses a key behavioral trait: the duplicate-check logic and optional override. However, it lacks details on permissions, rate limits, error handling, or what the response looks like (since no output schema exists).

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 zero waste—each sentence adds value (purpose and behavioral nuance). It's appropriately sized and front-loaded with the core purpose, though it could be slightly more structured (e.g., bullet points for behaviors).

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 (a write operation with behavioral nuance), no annotations, and no output schema, the description is moderately complete. It covers the core purpose and a key behavior but misses details like response format, error cases, or authentication requirements, leaving gaps 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 description coverage is 100%, so the schema already documents the 'title' parameter. The description adds no additional parameter semantics beyond what's in the schema (e.g., format constraints, examples). The baseline of 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the action ('Create a group or list') and the resource ('for the user'), making the purpose unambiguous. It doesn't explicitly distinguish from siblings like 'updateGroup' or 'getGroups', but the verb 'create' inherently differentiates it from read/update 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 implies usage context through the duplicate-check behavior ('If a group with the same name already exists...'), suggesting it's for creating new groups. However, it doesn't explicitly state when to use this versus alternatives like 'updateGroup' or provide prerequisites (e.g., authentication needs).

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it implies a write operation ('Create'), it doesn't address permissions, error handling, rate limits, or what happens on success/failure. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding its 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 extremely concise with two sentences that each serve a clear purpose: stating the tool's function and providing usage guidelines. There's no wasted language, and it's effectively 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 complexity (a simple creation operation with 2 parameters), 100% schema coverage, and no output schema, the description is minimally adequate. It covers purpose and usage but lacks behavioral details that would be helpful for a mutation tool without 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 100%, with both parameters ('contact_id' and 'content') fully documented in the schema. The description doesn't add any additional meaning or context beyond what the schema provides, so it meets the baseline score for high schema coverage.

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

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

The description clearly states the action ('Create a note') and target resource ('for a contact'), making the purpose unambiguous. However, it doesn't differentiate from sibling tools like 'getNotes' or 'searchInteractions' beyond the creation aspect, which prevents a perfect score.

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 usage guidance: 'Only use this when the user explicitly asks to create, add, or save a note.' This clearly defines when to invoke the tool versus alternatives, offering strong operational constraints.

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 states it 'gets details' which implies a read-only operation, but doesn't disclose behavioral traits such as authentication requirements, rate limits, error handling (e.g., what happens if the contact_id is invalid), or whether the data is real-time or cached. This is a significant gap for a tool with no annotation coverage.

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 front-loads the core purpose ('Get details for a contact by id') and adds useful specifics ('including emails, social links, phone numbers, and notes'). There is no wasted verbiage, and every word earns its place in clarifying the tool's function.

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 (a read operation with one parameter), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the return values look like (e.g., structure of the contact details), error conditions, or any prerequisites. For a tool with no structured support, more context is needed to be fully 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?

The input schema has 100% description coverage, with the parameter 'contact_id' clearly documented as 'The ID of the contact to get details for.' The description adds no additional meaning beyond this, such as format examples or constraints. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states the verb ('Get details') and resource ('for a contact'), specifying what information is retrieved (emails, social links, phone numbers, notes). It distinguishes from siblings like searchContacts (which finds contacts) and createContact (which creates new ones), but doesn't explicitly contrast with getNotes or getEvents which retrieve related but different data.

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 you need details for a specific contact by ID, suggesting an alternative to searchContacts for when you already have the ID. However, it doesn't explicitly state when NOT to use it or provide clear alternatives among siblings like getNotes (which might retrieve notes for a contact) or getEvents (which might retrieve events for a contact).

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 clearly indicates this is a read operation ('fetch'), but doesn't specify authentication requirements, rate limits, pagination behavior, or what happens if no events are found. It adds some context about date range usage but lacks comprehensive behavioral 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 perfectly concise with two sentences that each earn their place. The first sentence establishes the core purpose and usage context, while the second provides critical exclusion criteria. There's zero wasted language and it's effectively 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 read-only tool with 2 parameters and no output schema, the description provides good purpose and usage guidance but lacks information about return format, error conditions, or authentication requirements. The absence of annotations means the description should do more to compensate, particularly regarding behavioral transparency.

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

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

The schema description coverage is 100%, with both parameters thoroughly documented in the input schema. The description doesn't add any parameter-specific information beyond what's already in the schema descriptions. It mentions date range context but doesn't provide additional syntax or format 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 tool's purpose with specific verb ('fetch') and resource ('meetings/events'), and distinguishes it from sibling tools by specifying it's for fetching events rather than contacts, groups, notes, or interactions. It explicitly differentiates from counting, analyzing, or finding patterns.

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 usage guidelines with clear 'when to use' examples (e.g., 'what meetings next week?', 'show calendar for tomorrow') and explicit 'when not to use' exclusions (counting meetings, analyzing patterns, finding frequent participants). It effectively distinguishes this tool from potential 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 of behavioral disclosure. It states the tool retrieves data, implying it's read-only, but doesn't clarify aspects like authentication requirements, rate limits, pagination behavior (beyond the 'limit' parameter), or error handling. For a tool with no annotation coverage, this is a significant gap in 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, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it easy for an agent to parse quickly. This exemplifies good conciseness in tool descriptions.

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 and output schema, the description is incomplete for effective tool use. It doesn't explain what 'groups or lists' entail, how results are structured, or any behavioral traits like side effects. For a retrieval tool with no structured support, more context is needed to guide the agent adequately.

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 the 'limit' parameter clearly documented in the schema. The description adds no additional parameter information beyond what the schema provides, such as default values or usage examples. Given the high schema coverage, a baseline score of 3 is appropriate, as the description doesn't enhance parameter understanding.

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') and resource ('all groups or lists for the user'), making the purpose understandable. It distinguishes from siblings like 'createGroup' or 'updateGroup' by focusing on retrieval rather than modification. However, it doesn't specify whether this returns personal groups, shared groups, or both, which could be more precise.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention siblings like 'searchContacts' or 'aggregateContacts' that might be relevant for group-related queries, nor does it specify prerequisites such as authentication or context. This leaves the agent without clear usage direction.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool returns notes by creation date only (not content search), has strict usage constraints, and implies read-only operation through 'retrieve.' However, it doesn't mention potential limitations like rate limits, pagination, or authentication requirements, leaving some behavioral aspects uncovered.

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 appropriately sized and front-loaded with the core purpose and usage rules. Every sentence serves a clear purpose: establishing usage constraints, describing functionality, and prohibiting misuse. While slightly repetitive with the 'note/notes' emphasis, it maintains efficiency without 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 tool's moderate complexity (2 required parameters, no output schema, no annotations), the description provides good contextual coverage. It explains what the tool does, when to use it, and behavioral constraints. The main gap is the lack of output format details (since no output schema exists), but the description compensates well with clear functional boundaries and usage rules.

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

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

Schema description coverage is 100%, providing detailed format examples for both parameters. The description adds minimal parameter semantics beyond the schema, only mentioning 'between two dates' which is already implied by the parameter names. The baseline score of 3 is appropriate since the schema does the heavy lifting, though the description doesn't add meaningful additional context about 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?

The description clearly states the tool's purpose: 'retrieve notes between two dates' with specific verb+resource. It explicitly distinguishes from sibling tools by stating it 'does NOT search note content or filter by other criteria' and contrasts with tools like getContact, searchContacts, etc. The distinction from content search and other entity types is well-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?

The description provides explicit usage rules: 'Use ONLY when the user explicitly mentions "note" or "notes"' and 'NEVER use this tool for finding contacts or any other purpose.' It gives concrete examples ('e.g. "what notes from last week?"') and clear prohibitions. The guidance is comprehensive with specific when/when-not 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions what the tool returns ('actual contact records'), it lacks critical behavioral details: whether this is a read-only operation, how results are paginated (though limit parameter exists), error conditions, authentication requirements, or rate limits. For a search tool with 8 parameters, 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 appropriately sized with three sentences that each serve distinct purposes: stating the core function, providing usage examples, and specifying return type. It's front-loaded with the main purpose and avoids unnecessary elaboration. Minor improvement could be made by combining the second and third sentences.

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 search tool with 8 parameters, no annotations, and no output schema, the description is incomplete. While it covers purpose and usage well, it lacks critical behavioral context about how the search works, what 'actual contact records' contain, error handling, and performance characteristics. The absence of output schema means the description should ideally explain return format, which it doesn't.

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

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

Schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. However, it does provide context about the overall search intent ('who' questions), which gives semantic meaning to the parameter usage collectively.

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 purpose with specific verbs ('search for contacts and return matching people') and distinguishes it from siblings by specifying it's for 'who' questions and returning 'actual contact records'. It differentiates from tools like getContact (single contact) and searchInteractions (interactions rather than people).

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 guidance on when to use this tool: 'for questions about specific contacts or "who" questions' with concrete examples ('Who did I meet most?' or 'who works as an engineer?'). It also specifies the return type ('actual contact records for queries needing specific people'), helping differentiate from other contact-related 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 tool returns 'actual contact records' and mentions 'relevance score' for ranking, which adds useful context. However, it doesn't describe important behavioral aspects like pagination, rate limits, error conditions, or whether this is a read-only operation (implied by 'search' but not explicit).

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

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

The description is appropriately concise with two sentences. The first sentence states the core purpose, and the second provides usage examples and clarifies the return type. Every sentence adds value, though the second sentence could be slightly more structured by separating use cases more clearly.

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 search tool with 8 parameters, 100% schema coverage, and no output schema, the description provides adequate context about purpose and usage. However, it lacks details about the return format (beyond 'actual contact records'), result limitations, or how the search algorithm works. Given the complexity of the parameter schema, more behavioral context would be beneficial.

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

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

The schema has 100% description coverage, so parameters are well-documented in the schema itself. The description doesn't add any specific parameter information beyond what's in the schema, but it does provide context about what types of queries the tool handles (e.g., 'who' questions, finding best friends), which helps understand how to use the parameters effectively.

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 purpose: 'Search for interactions and return matching interactions.' It specifies the verb ('search') and resource ('interactions'), and provides concrete use cases like answering 'who' questions or finding best friends. However, it doesn't explicitly differentiate from the sibling 'searchContacts' tool, which appears to be a related search 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?

The description provides clear guidance on when to use this tool: 'for questions about specific interactions, "who" questions, finding best friends based on relevance score, or finding recently added/created contacts.' It gives specific scenarios but doesn't explicitly state when NOT to use it or mention alternatives like 'searchContacts' for comparison, which would be needed for a perfect score.

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 clearly indicates this is a mutation tool ('Update'), which implies it modifies data. It adds useful context about batch operations for contacts, warning against multiple calls. However, it lacks details on permissions needed, error handling (e.g., invalid IDs), rate limits, or whether changes are reversible. For a mutation tool with zero annotation coverage, this leaves gaps in behavioral understanding.

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 appropriately sized and front-loaded: it starts with the core purpose, then adds a critical usage guideline. Both sentences earn their place by providing essential information without redundancy. No wasted words or 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 tool's complexity (mutation with 4 parameters), no annotations, and no output schema, the description is moderately complete. It covers the purpose and a key behavioral guideline but misses details like response format, error cases, or prerequisites. For a mutation tool, more context would be helpful, but it's adequate as a minimum viable 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?

Schema description coverage is 100%, so the schema fully documents all parameters (group_id, title, add_contact_ids, remove_contact_ids). The description adds minimal value beyond the schema, only implying that title and members can be updated. It doesn't provide additional semantics like format examples or constraints not in the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Update a group or list' with specific actions 'update the group title and/or modify its members.' It distinguishes from siblings like createGroup (creation vs. update) and getGroups (read vs. update). However, it doesn't explicitly contrast with all possible alternatives like modifyGroup if such existed.

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 guidance: 'When adding or removing contacts, provide ALL contact IDs to add/remove in a single call - do not make multiple calls for individual contacts.' This is explicit about how to use the tool effectively. However, it doesn't specify when to use this tool versus alternatives like createGroup for new groups or getGroups for viewing, nor does it mention prerequisites like needing an existing group_id.

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