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

No annotations provided, so the description must cover behavioral traits. It mentions role assignment and default, and that a success message is returned, but does not disclose rate limits, idempotency, or error conditions (e.g., duplicate participant). Adequate but not comprehensive.

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 structured with intro, conditions, list, suggestion, Args, and Returns. Every sentence adds value, though the list of acceptable additions could be more compact. Clear and well-organized.

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 (3 params, default role, prerequisites), the description covers the action, prerequisites, parameter details, discoverability hint, and return value. An output schema exists, so return structure is not needed. 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?

Schema description coverage is 0%, so the description fully explains all three parameters in the Args section: chat_id, participant_id, and role with allowed values and default. This adds critical 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 'Add a participant (agent or user) to a chat room.' using a specific verb and resource. It distinguishes from siblings like 'add_my_chat_participant' by specifying the chat room context and participant types.

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 conditions: the acting agent must be owner/admin, lists who can be added (sibling agents, global agents, owner), and suggests using 'list_agent_peers' to discover participants. This gives clear guidance on when and how to use the tool.

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

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

No annotations are provided, so the description carries full burden. It discloses the mutual approval behavior and that it initiates a request, but does not cover error cases, permissions, or side effects like existing contacts.

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

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

The description is concise with a single purpose sentence followed by structured args and returns. 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 presence of an output schema, the description adequately covers the action and mutual case. It could mention edge cases or prerequisites but remains complete for most usage.

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

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

Schema coverage is 0%, so the description compensates by explaining 'handle' as 'The handle of the entity' and 'message' as 'Optional message'. This adds meaning beyond the schema's type-only definitions, but lacks formatting or constraint details.

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

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

The description clearly states the verb 'Send a contact request' and specifies the resource 'to another entity by handle'. It distinguishes from sibling tools like 'approve_contact_request' and 'respond_to_agent_contact_request' by noting the mutual approval behavior.

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

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

It explains the action (initiating a contact request) and the condition for automatic approval (mutual). However, it lacks explicit guidance on when not to use this tool versus alternatives like 'create_contact_request' or 'respond_to_agent_contact_request'.

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

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

With no annotations, the description bears full burden. It states the action but does not disclose permissions, side effects, reversibility, or any behavioral traits beyond the parameter 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 docstring-style description is concise and well-structured, with each sentence adding value. No unnecessary words or repetition.

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

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

Given moderate complexity, the description covers basic purpose and parameters but omits preconditions, usage context, and output description. Since an output schema exists, the lack of return value information is acceptable, but more context would improve completeness.

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

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

The description adds meaning beyond the schema by enumerating role values ('owner', 'admin', 'member') and stating a default of 'member'. It clarifies chat_id as 'chat room ID' and participant_id as 'ID of user or agent', compensating for 0% 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 'Add a participant to a chat room,' using a specific verb and resource. It distinguishes itself from removal tools but does not explicitly differentiate from sibling 'add_agent_chat_participant'.

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 lists required and optional parameters with defaults, providing usage guidance. However, it lacks context on when to use this tool versus alternatives (e.g., add_agent_chat_participant) and does not mention prerequisites or exclusions.

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

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

No annotations are provided, so the description must carry the full burden. It only states the return type (JSON string) but does not disclose behavioral traits such as side effects (e.g., adding a contact), required permissions, or irreversibility.

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 concise with two sentences, front-loaded with the action, and every word is necessary. No wasted text.

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

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

Given the simple input (one parameter) and presence of an output schema, the description is adequate but lacks behavioral context. It does not explain what happens after approval (e.g., if the contact is automatically added) or if the action is reversible.

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 zero description coverage, but the description adds clear meaning to the parameter 'request_id' by stating it is the contact request ID to approve and that it is required.

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 approves a received contact request, using a specific verb and resource, and it implicitly distinguishes from sibling tools like reject_contact_request and cancel_contact_request.

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 that the tool should be used when approving a received request, but it does not explicitly mention when not to use it or provide alternatives. Siblings are not referenced.

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

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

No annotations are provided, so the description must carry the full burden. It only mentions cancellation and return format, but lacks disclosure of side effects, permissions, error handling, or idempotency.

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

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

The description is short and includes an Args section, but is under-specified. It could be more informative without increasing length significantly.

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 cancellation tool, the description is minimal but lacks details on error cases, idempotency, and what 'cancelling' entails. The output schema is present but not described.

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 merely restates the schema ('The contact request ID to cancel (required).'). It adds no additional meaning about the parameter's format, constraints, or behavior.

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

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

The description clearly states the action (cancel) and the resource (sent contact request). However, it does not differentiate from sibling tools like 'reject_contact_request' or 'respond_to_agent_contact_request'.

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

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

No guidance on when to use this tool versus alternatives. The description only states what it does without any context about prerequisites or exclusions.

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

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

No annotations are provided, so the description carries the full burden. It discloses ownership behavior and optional task association but does not detail side effects (e.g., permissions, notification, error handling). Adequate but not rich for a mutation tool.

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

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

The description is structured with a concise summary line, followed by details, clear Args/Returns sections, and no extraneous content. 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?

For a simple tool with one optional parameter and an output schema, the description covers purpose, parameter usage, return format, and ownership. No gaps given the tool's complexity.

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

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

Schema coverage is 0%, so the description must compensate. It provides a clear explanation of the 'task_id' parameter as 'Optional ID of an associated task', adding meaning beyond the schema's type-only definition.

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 ('Create a new chat room') and the resource ('the agent as owner'), clearly distinguishing it from sibling tools like 'create_my_chat' which likely creates a user-owned chat.

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 mentions the optional task association but does not explicitly guide when to use this tool versus alternatives like create_my_chat. It implies use for agent-owned chats but lacks explicit when-not-to-use guidance.

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

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

No annotations provided, so description bears full burden. It explains events don't require mentions and describes event type structures. But it does not disclose whether events persist, visibility, required permissions, or side effects.

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

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

Well-structured with headers, bullet lists, and examples. Slightly verbose but every section adds value. Could trim redundant 'human-readable' phrases.

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

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

Covers purpose, parameter semantics, event types, sibling differentiation, and provides examples. Missing behavioral context like persistence and permissions, but otherwise complete for a 4-parameter tool with output schema.

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

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

Adds significant detail beyond the schema: chat_id as unique identifier, content as human-readable, message_type as enum with allowed values explained via examples, metadata as optional JSON with structure by type. The 0% schema coverage makes this critical and it delivers.

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 it posts events in a chat room, lists five specific event types, and explicitly differentiates from create_agent_chat_message for text messages with mentions. Uses a specific verb 'post' and resource 'event'.

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 says to use create_agent_chat_message for text messages with mentions, and notes events don't require mentions. However, it doesn't detail when to use each event type or contrast with other tools like send_my_chat_message.

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

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

No annotations provided, so description carries full burden. It discloses the @mention requirement, recipient resolution behavior, and precedence rules. However, it does not mention error handling or permissions, though these are minor omissions for a create 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?

Well-structured with sections and examples, but slightly lengthy. Every sentence adds value, but could be tighter. Front-loaded with core purpose.

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

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

Covers all aspects: purpose, parameters, usage guidelines, return value (JSON string). Sibling tool create_agent_chat_event is mentioned for event messages. Complete for an agent to select and invoke correctly.

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

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

Schema description coverage is 0%, but description adds extensive meaning: explains chat_id, content, recipients (comma-separated names), mentions (JSON array), precedence rules, and examples. This fully compensates for the lack of schema descriptions.

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

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

The description clearly states the tool sends a text message in a chat room and differentiates it from create_agent_chat_event for event-type messages. The verb 'send' and resource 'text message' are explicit.

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

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

Provides explicit guidelines: must include at least one @mention, two ways to specify recipients (LLM-friendly vs. pre-resolved), and when to use each. Also directs to an alternative tool for event-type messages.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only mentions the return type (JSON string) but does not discuss mutation aspects, error conditions, idempotency, or authentication needs. Minimal behavioral context.

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

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

The description is concise: one sentence for purpose, followed by structured Args and Returns sections. No unnecessary words, front-loaded with purpose.

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

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

Given the tool's simplicity (2 params, no nested objects), the description covers the basics well. However, it lacks broader context such as error handling, asynchronous behavior, or how this fits with sibling tools. An output schema exists, so return values are partially documented, but no further 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 description adds meaning beyond the input schema: it specifies the handle format (with/without @ prefix), requiredness, and max character count for message. Schema coverage is effectively 100% from the description, and it provides constraints not in 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 'Send a contact request to another user,' which is a specific verb+resource combination. It distinguishes from sibling tools like approve_contact_request and cancel_contact_request.

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

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

The description implies when to use the tool (to initiate a contact request) but does not explicitly state when not to use it or provide alternative guidance. Context from sibling tools suggests related operations, but the description lacks direct comparison.

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

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

No annotations are provided, so the description must cover behavioral traits. It states creation and ownership but lacks details on permissions, idempotency, or side effects. Minimal disclosure for a mutation tool.

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

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

Two sentences, no redundancy. Purpose is stated first, followed by parameter explanation. Every word serves a purpose.

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

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

Given the simplicity of the tool (one optional parameter, no nested objects) and presence of an output schema, the description is minimally adequate. However, it does not differentiate from siblings or clarify the chat room concept. Lacks completeness for full context.

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

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

The description adds semantic value to the 'task_id' parameter by stating it is 'Optional task ID to associate with the chat'. Schema coverage is 0%, so this brief explanation is helpful but does not fully compensate.

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

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

The description clearly states the verb 'create' and the resource 'chat room with the user as owner'. This distinguishes it from sibling 'create_agent_chat' which creates an agent chat. No ambiguity.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'create_agent_chat' or scenarios requiring participant addition. No exclusions or context for usage.

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

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

No annotations are provided, so the description carries full burden. It does not disclose behavioral traits such as read-only nature, potential errors (e.g., invalid chat_id), or access restrictions. It only states that it retrieves information without any additional behavioral context.

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

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

The description is front-loaded with the main purpose, followed by a brief explanation and a clear Args section. No unnecessary words, and the structure is efficient and easy to parse.

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

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

Given no annotations and only one parameter, the description is fairly complete. However, it could provide more detail about the return value (e.g., fields included in the JSON string) to help the agent understand what to expect.

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

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

Schema description coverage is 0%, so the description adds value by explaining 'chat_id: The unique identifier of the chat room (required).' This adds meaning beyond the schema's title and type, though it could specify format or source of the 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 'Get a specific chat room by ID' and specifies that it retrieves detailed information about a single chat room where the agent is a participant. This is specific and distinct from sibling tools like list_agent_chats or create_agent_chat.

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 have a chat_id but does not explicitly state when to use this tool versus alternatives. It provides the required parameter, which guides usage, but lacks exclusion criteria or mention of alternatives.

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

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

With no annotations, the description carries full burden. It discloses chronological order and message types included. However, it does not mention authentication requirements, rate limits, or behavior for edge cases (e.g., empty chat, large pages). It covers the basics but lacks some operational 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 well-structured with bullet points for included content and a clear Args section. It is concise, every sentence adds value, and the important 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 that an output schema exists, the return description is sufficient. The tool covers what it does, when to use it, and parameters. Minor gaps like error handling or empty results are not addressed, but overall it is complete for its purpose.

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 all three parameters: chat_id as required identifier, page and page_size with defaults and max. This adds significant value beyond the schema's bare titles.

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

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

The description clearly states the tool retrieves conversation context for agent rehydration, specifying exactly which messages are included (all agent-sent messages and @mentions). It distinguishes itself from siblings like get_agent_next_message or list_agent_messages by explicitly stating its use case for rehydration.

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 load the complete context a remote agent needs to resume execution,' providing clear guidance on when to use it. It does not mention when not to use it or directly name alternative tools, but given the sibling list, the context is clear enough for an AI agent.

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

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

With no annotations, the description clearly indicates this is a read-only operation (returns profile) and serves as connection validation. However, it does not mention any potential side effects or authentication requirements beyond validation.

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

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

The description is concise (4 lines), front-loads the main purpose, and includes useful extra information (connection validation) without unnecessary detail.

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

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

Given the simplicity (no parameters, output schema present), the description is fully complete: it states purpose, return content, and a use case. The output schema handles return value details.

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

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

The input schema has no parameters with 100% coverage, so the description need not add parameter details. Baseline 3 is appropriate.

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

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

The description clearly states 'Get the current agent's profile' and specifies the contained fields (ID, name, description, metadata). It distinguishes from siblings as it uniquely targets the authenticated agent.

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 mentions connection validation as a use case, but fails to differentiate from the similar sibling tool 'get_my_profile'. No explicit when-not-to-use or alternative guidance.

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

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

With no annotations provided, the description fully discloses behavioral traits such as returning messages in various states (new, delivered, processing, failed), handling crash recovery by returning stuck messages, and returning empty results when none exist. 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 well-structured with sections and bullet points, front-loaded with the main purpose. While slightly lengthy, every sentence adds value, explaining behavior, usage, and comparison. It earns its length.

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

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

Given a single parameter and an output schema, the description is complete. It covers return values (JSON string or empty), behavior (oldest first, includes stuck messages), and use cases (sequential processing loops). 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 adds an 'Args' section explaining 'chat_id' as 'The unique identifier of the chat room (required)', which adds meaning beyond the input schema's title 'Chat Id'. Schema coverage is 0%, so the description compensates well.

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 'Get the next message that needs processing' and specifies it returns the single oldest unprocessed message. It explicitly distinguishes from the sibling tool 'list_agent_messages' which returns all messages, providing strong differentiation.

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 step-by-step workflow for an agent reasoning loop, explaining when to call this tool (to get the next work item) and explicitly contrasts with 'list_agent_messages' for batch processing. It also covers crash recovery 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?

No annotations provided; description only restates the action. Does not disclose error handling, access control, or whether the chat must belong to the user.

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

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

Extremely concise with two sentences. The primary action is front-loaded with no extraneous information.

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

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

For a simple retrieval tool, the description is minimally functional but lacks context on output, error cases, and ownership requirements. An output schema exists but is not shown.

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 adds minimal value by restating that chat_id is required. Does not explain expected format or constraints (e.g., UUID).

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

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

The description clearly states the verb 'Get' and the resource 'specific chat room by ID', making the action unambiguous. It distinguishes from sibling tools like 'create_my_chat' or 'list_my_chats'.

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

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

No guidance on when to use this tool versus alternatives like 'get_agent_chat' or 'list_my_chats'. No conditions or prerequisites mentioned.

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

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

No annotations are provided, so the description must cover behavioral traits. It only states that the tool returns profile information without mentioning idempotency, side effects, or authentication requirements. The read-only nature is implied 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 two short, front-loaded sentences with no superfluous information. Every word serves a purpose.

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

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

Given the tool's simplicity (zero parameters, output schema exists), the description provides sufficient context for an agent to understand the action and expected output. No additional details are necessary.

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

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

There are zero parameters, and the schema coverage is 100%. The description adds no information about parameters beyond the schema, but the baseline is 3 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 'Get the current user's profile details' and lists included fields, making the purpose unambiguous. It distinguishes this tool from sibling tools like update_my_profile or get_agent_me.

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

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

The description implies the tool is for retrieving one's own profile, but it does not explicitly state when to use it over alternatives or exclude other scenarios. No guidance on prerequisites.

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

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

The description does not disclose behavioral traits beyond the basic action. With no annotations provided, the description carries the full burden, but it fails to indicate whether the operation is read-only, destructive, or has side effects. A health check is likely safe, but this is not stated.

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

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

The description is a single sentence with no wasted words. It is appropriately sized for a simple health check tool.

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

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

Given the tool's simplicity (no parameters, trivial purpose) and the presence of an output schema, the description is nearly complete. It could mention the expected success/failure indicator, but the output schema likely covers that.

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

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

There are zero parameters, so the input schema is trivially covered. The description does not add parameter semantics, but none are needed. Baseline score of 4 is appropriate.

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

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

The description clearly states the tool's purpose: 'Test MCP server and API connectivity.' It uses a specific verb ('Test') and resource ('MCP server and API connectivity'), and it is distinct from all sibling tools which are focused on chat/contact management.

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

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

No explicit guidance on when to use this tool vs alternatives. However, since no sibling tool performs a health check, usage context is implied. A higher score would require explicit when-to-use or when-not-to-use statements.

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

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

No annotations exist, so the description must carry full burden. It only states it retrieves participants and returns JSON, without revealing side effects, error behavior, or authorization requirements. This is minimal for a read operation.

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

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

The description is concise, with clear Args and Returns sections. Every sentence adds value, and the structure is optimal for agent consumption.

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

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

For a simple tool with one parameter, the description is adequate. However, it lacks details on error scenarios, authentication, or the scope of participants (e.g., active vs. all). An output schema exists but is not detailed in the 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 coverage is 0%, but the description adds meaning by labeling chat_id as 'the unique identifier of the chat room (required)'. This provides basic context beyond the schema's type, but does not offer format or constraints.

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

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

The description clearly states the tool lists participants in a chat room, specifying 'where the agent is a member'. This distinguishes it from general participant listing tools, though the difference from list_my_chat_participants is not explicitly clarified.

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

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

Usage is implied (for agent-member chats) but no explicit guidance on when to use versus siblings like add_agent_chat_participant or list_my_chat_participants. No exclusions or prerequisites mentioned.

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

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

No annotations provided; description does not disclose behavioral traits such as authentication requirements, rate limits, or side effects beyond stating it returns a JSON string of chat rooms.

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?

Description is concise and well-structured with clear Args/Returns sections. No redundant information, but 'Args:' formatting adds slight verbosity.

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?

Adequate for a simple list tool with pagination. However, given existence of sibling tools and no output schema details, it could include more context about the structure of the returned JSON.

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%, so description adds meaning by explaining page and page_size as pagination controls. This compensates for the lack of schema descriptions.

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

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

The description clearly states the action (List), resource (chat rooms), and scope (agent participant). It is specific and distinguishable from similar list tools, though it does not explicitly contrast with siblings like list_my_chats.

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., list_my_chats). Mentions pagination but lacks exclusions or context for selective 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?

No annotations provided, so description must disclose behavior. It states that both received and sent requests are returned, and sent_status filters sent requests. It does not explicitly state read-only nature, but it's a list operation and description implies no 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?

Description is concise with a clear intro, then Args section, then Returns line. No unnecessary words, and 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?

With an output schema present, the description adequately covers return format. It could mention pagination defaults or error conditions, but it's sufficient for an agent to use correctly.

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

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

Schema coverage is 0%, but description fully documents all three parameters with types, defaults, and enum values for sent_status. This adds significant meaning beyond the bare schema types.

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 'List the agent's contact requests (both sent and received).' This differentiates from sibling tools like list_received_contact_requests and list_sent_contact_requests by combining both types in one call.

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 explains use of sent_status filter, and the context of siblings implies when to use this combined version vs separate lists. However, no explicit 'when not to use' or alternative tool names are mentioned.

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

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

With no annotations, the description adequately discloses behavior: it lists approved mutual contacts, mentions returned fields (handle, name, type, description), and supports pagination. 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 concise, front-loaded with the main action, uses clear sections (Returns, Args, Returns), and every sentence adds value without redundancy.

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

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

For a simple listing tool with two optional parameters, the description covers purpose, return fields, and pagination. Output schema exists, reducing need for further detail.

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

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

Input schema lacks parameter descriptions (0% coverage), but the description explains page and page_size as optional pagination parameters, adding meaning beyond the schema's type info.

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

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

The description clearly states 'List the agent's contacts' and specifies they are 'approved (mutual connections)', distinguishing it from sibling tools like list_my_contacts or list_agent_peers.

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 indicates the tool returns only mutual contacts, implying use case for retrieving approved connections, but lacks explicit when-not or alternative tool guidance.

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

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

Without annotations, the description covers default behavior, chronological ordering, and return type (JSON string). It does not mention rate limits, auth needs, or error handling, but provides sufficient context for safe use.

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 well-structured with clear sections (default, status options, sorting, workflow, args). Every sentence adds value and it is front-loaded with the main purpose. 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 4 parameters, no annotations, and an output schema (implied), the description covers filtering, pagination, sorting, and workflow adequately. It explains return value as 'JSON string containing list of messages', which is sufficient.

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

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

Input schema has 0% description coverage, so the description fully compensates. It explains each parameter: chat_id required, status options with detailed meanings, page and page_size with defaults and max.

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 messages that the agent needs to process, filtered by status.' It specifies the resource (agent messages) and action (list). It distinguishes from sibling tool 'get_agent_next_message' by referencing it in the workflow.

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 explains default behavior (no status returns actionable messages) and when to use each status filter. It provides a workflow after retrieval, listing alternative tool 'get_agent_next_message' in step 1.

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

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

With no annotations, the description discloses the return behavior (list of peers), inclusion/exclusion criteria, and return format. No side effects are mentioned, but the operation is read-only.

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

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

The description is concise and well-structured: a one-line summary, a brief paragraph, and a bulleted Args list. Every sentence adds value with 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?

The description covers functionality, parameters, and return type adequately for a list tool. Missing details like pagination defaults or limits, but overall sufficient.

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, but the tool description includes an Args section that fully explains each parameter (not_in_chat, page, page_size), adding significant meaning beyond types and defaults.

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

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

The description clearly states the tool lists agents that can be recruited by the current agent, includes sibling and global agents, and excludes self. The purpose is specific and distinct from siblings like list_my_peers.

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 context on when to use the not_in_chat parameter, but does not explicitly compare to alternative tools or state when not to use the tool.

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

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

No annotations provided; the description only states the basic action. It does not disclose read-only nature, authentication requirements, rate limits, or any side effects. The description fails to compensate for missing annotations.

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

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

The description is appropriately short and includes an Args section. It is well-structured and avoids unnecessary verbosity.

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 (2 optional parameters, no required, output schema exists), the description provides minimal but acceptable completeness. However, it lacks behavioral context that would be helpful for an agent.

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

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

Schema description coverage is 0%. The description repeats parameter names (page, page_size) without adding any semantic meaning, constraints, or default behaviors beyond what is already in the schema.

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

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

The description clearly states the action (List) and the resource (agents owned by the user). It distinguishes from siblings like list_my_contacts and list_my_chats by specifying ownership and agent 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?

No guidance on when to use this tool versus alternatives. For example, it doesn't explain when to use list_my_agents vs list_agent_chats or other list 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?

No annotations are provided, and the description does not disclose behavioral traits such as whether pagination is zero-indexed, maximum page size, rate limits, authentication requirements, or error behaviors. It only lists parameters without explaining operational semantics.

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

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

The description is concise with a clear Args list. It avoids extraneous content and front-loads the core purpose. Each sentence serves a purpose, though it could be slightly more streamlined.

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 are not required. However, the description lacks mention of ordering, default pagination behavior, or any edge-case handling, which are important for a listing tool with multiple optional filters.

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 adds useful details: 'page number', 'items per page', filter by type examples ('text', 'tool_call'), and 'ISO 8601 timestamp'. However, it does not specify default values or constraints beyond what the schema implies.

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 messages in a chat room', which is a verb (list) and resource (messages). It differentiates from sibling tools like 'list_agent_messages' by the 'my' prefix, but doesn't explicitly clarify that it lists the user's own chat messages.

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

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

The description provides no guidance on when to use this tool vs alternatives like 'list_agent_messages' or 'list_my_chats'. No context about prerequisites or preferred 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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'List participants' without mentioning pagination, ordering, permission requirements, error cases, or whether it returns all or only visible participants. This is a significant gap for a read operation.

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

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

The description is very brief, using two lines for text and two for arguments. It is efficient but could benefit from a one-line summary of purpose before the args. No unnecessary 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?

Despite having an output schema (not provided), the description does not explain return structure, error handling, or scope (my chats vs agent chats). With no annotations, a minimal description like this is incomplete for an agent to reliably use the tool without additional context.

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

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

The schema has 0% description coverage, but the description adds meaning: chat_id is labeled as 'The chat room ID (required)' and participant_type as 'Filter by type: 'User' or 'Agent' (optional)', which clarifies usage and specifies allowed values beyond the schema's bare type definitions.

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 participants in a chat room' with specific arguments for chat_id and participant_type, making the action and resource clear. However, it does not distinguish from sibling tool list_agent_chat_participants by noting the scope (my chats vs agent chats), which slightly reduces clarity.

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

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

No guidance is given on when to use this tool versus alternatives like add_my_chat_participant, remove_my_chat_participant, or list_agent_chat_participants. The description lacks context on prerequisites or exclusions, making it insufficient for an agent to decide optimal usage.

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

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

No annotations exist, so the description carries full behavioral disclosure burden. It only states the basic function without mentioning pagination behavior, rate limits, ordering, or any side effects. The output schema exists but is not described.

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

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

The description is extremely concise with a one-line purpose and two parameter descriptions. There is no fluff or redundancy, earning high marks for efficiency.

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

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

For a simple list tool with pagination, the description provides basic purpose and parameter hints. However, it lacks details such as default values (though schema shows defaults), ordering, and whether pagination yields all pages. The output schema exists but is not described, which is acceptable. The description is adequate but not comprehensive.

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

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

The schema description coverage is 0%, but the description adds meaningful info: 'Page number (optional)' and 'Items per page (optional)' clarifies the parameters' roles and optionality beyond the schema's type and 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?

The description clearly states it lists chat rooms where the user is a participant, which is a specific verb and resource. However, it does not differentiate from sibling tools like list_agent_chats for agents or list_my_chat_messages for messages, leaving some ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of context, prerequisites, or exclusions, leaving the agent without direction.

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

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

Description states it lists active contacts and returns details, implying read-only. But without annotations, it fails to mention authentication, rate limits, or sorting behavior. Adequate but not exhaustive.

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

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

Description is short and front-loaded with the main purpose. The Args and Returns sections are clear but slightly redundant given the output schema. Still concise overall.

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 paginated list, the description covers input and output basics. Missing default pagination behavior, sorting order, and handling of empty results. Adequate but incomplete.

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

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

Schema coverage is 0% (no parameter descriptions in schema). The description adds 'page number for pagination' and 'number of items per page', but doesn't explain defaults (null) or behavior when omitted. Minimal added 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?

The description clearly states the tool lists the user's contacts, specifying it returns active contacts with details like handle, email, and type. This clearly distinguishes it from sibling tools like 'list_agent_contacts' or 'remove_my_contact'.

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

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

No guidance on when to use this tool versus alternatives like 'list_my_peers' or 'list_my_agents'. No not-use conditions or prerequisites are mentioned.

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

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

No annotations provided. The description indicates a read operation and mentions parameters for filtering, but lacks details on pagination behavior, authentication requirements, or whether global agents are always included. It does not contradict any annotations (none present), but more behavioral context would be helpful.

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 brief with a clear structure: a purposeful sentence, an explanatory sentence, and a parameter list. No redundant information. Could be slightly more compact, but effective.

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 description doesn't need to explain return values. It adequately covers the tool's purpose and parameter semantics. Only minor gaps like default pagination limits or whether result ordering is defined.

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 compensates by explaining each parameter's purpose: not_in_chat excludes entities already in a chat, peer_type filters by 'User' or 'Agent', page/page_size for pagination. This adds meaningful context beyond the schema's types and names.

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

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

The description clearly states it lists entities you can interact with in chat rooms, specifying peers include other users, agents, and global agents. This effectively distinguishes it from siblings like list_my_agents (lists your own agents) and list_my_contacts (contacts).

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

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

The description implies the tool is for listing available participants for chat rooms, but it doesn't explicitly state when to use this over alternatives. No exclusion or comparison with similar list tools (e.g., list_my_contacts, list_agent_peers). An agent might infer usage from context, but guidance is 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?

Given no annotations, the description discloses that the tool returns only pending contact requests (not all received), is a read operation, and provides pagination. It could mention if requests are sorted or if any filtering applies, but it adequately covers the core 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 concise (4 short sentences) with clear sections for Args and Returns. Every sentence adds value without redundancy.

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

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

For a simple list tool with two optional parameters and an output schema, the description fully covers purpose, state (pending), and pagination. No gaps given the low 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 input schema has 0% coverage, but the description explains both parameters (page and page_size) as optional pagination controls, which adds meaningful context beyond the schema types.

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 lists 'received contact requests' and specifies that it returns pending ones needing approval or rejection. It distinguishes from siblings like list_sent_contact_requests by the direction (received vs sent) and status (pending).

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 indicates this tool is for viewing pending requests that require action (approval or rejection). It implicitly guides the user to use this tool when they want to see incoming requests needing response, though it doesn't explicitly state when not to use it or mention alternatives.

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

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

With no annotations, the description must fully disclose behavior. It only states it returns a JSON string but omits key traits like read-only nature, pagination defaults, sorting order, or whether status filter is case-sensitive. This is insufficient for safe invocation.

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

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

The description is short and well-structured with bulleted parameter explanations and a returns line. Every sentence is necessary, and there is no extraneous information.

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

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

For a simple list tool with pagination and filter, the description covers basic usage but lacks details on pagination behavior, filter interactions, and any limitations. The existence of an output schema helps, but the description alone is only minimally complete.

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

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

Schema coverage is 0%, so the description is the sole source. It explains status with listed values and describes page/page_size briefly. However, it does not specify default behaviors (e.g., null page returns all), leaving gaps that the schema alone cannot fill.

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 contact requests sent by the user.' It uses a specific verb-resource combination and distinguishes well from siblings like list_received_contact_requests and list_agent_contact_requests, indicating sent vs. received or agent-specific scope.

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

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

The description implies the tool is for sent requests but does not explicitly state when to use it over alternatives like list_received_contact_requests. No guidance on when not to use or prerequisites is provided, leaving the agent to infer from context.

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

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

Describes all automatic actions: sets completed_at, status to 'failed', records error, updates delivery status. Also mentions error case (422) if no active attempt. With no annotations, this is thorough.

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?

Concise, well-structured: purpose sentence, usage instruction, bullet list of automatic actions, prerequisite note, and clear parameter descriptions. No extraneous 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?

Fully covers the operation: explains what it does, prerequisites, parameters, and return value. References sibling tools. Complete for a simple mutation tool with 3 required params.

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

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

The description adds meaning beyond schema: explains each parameter (chat_id, message_id, error) is required and provides brief rationale. Despite 0% schema coverage, the description compensates adequately.

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

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

The description clearly states the verb and resource: 'Mark a message processing as failed by the agent.' It distinguishes from sibling tools like 'mark_agent_message_processing' and 'mark_agent_message_processed' by contrasting when to call each.

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 says when to use: 'Call this when the agent cannot process a message.' Also provides a prerequisite: requires an active processing attempt, and directs to call 'mark_agent_message_processing' first if not.

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

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

With no annotations, the description carries full burden and details what the endpoint automatically sets (timestamps, statuses) and error condition (422 if no attempt). However, it lacks detail on return structure beyond 'Success message', though 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?

Description is well-structured with sections, concise yet thorough, no redundant sentences, and front-loaded with purpose.

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

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

Given the tool's simplicity (2 required params, no nested objects, output schema exists), the description covers purpose, usage, parameters, behavior, error condition, and prerequisites completely.

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% (no descriptions in schema), but the description includes an 'Args' section that adds clear meaning: 'unique identifier of the chat room' and 'ID of the message to mark as processed', fully compensating for the schema gap.

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

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

The description clearly states the action 'Mark a message as successfully processed by the agent' and differentiates from siblings like mark_agent_message_processing and mark_agent_message_failed by specifying the success outcome and prerequisite.

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 when to call ('when the agent finishes processing a message successfully'), the prerequisite ('Requires an active processing attempt...Call mark_agent_message_processing first'), and hints at the alternative for failure.

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 alone must disclose behavior. It details automatic actions like creating an attempt, setting status, recording timestamps, and updating delivery status. Missing idempotency or error scenarios, but overall quite transparent.

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 moderately long but well-structured with a purpose statement, bullet list of automatic behaviors, and separated args/returns sections. No unnecessary 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?

Given the two parameters and presence of output schema, the description covers the tool's function, usage, side effects, and return value. It is adequate for an agent to understand and invoke correctly, though error handling is not mentioned.

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, but the description includes an 'Args' section explaining each parameter (chat_id, message_id) with required status, adding meaning beyond the schema field names.

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

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

The description clearly states the tool marks a message as being processed by the agent, with specific verb and resource. It is easily distinguished from sibling tools like 'mark_agent_message_failed' and 'mark_agent_message_processed'.

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 'Call this when the agent starts working on a message', providing clear usage context. However, it does not mention when not to use it or alternative tools, leaving some room for improvement.

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?

Discloses that the API key is shown only once, which is a critical behavioral trait for a registration tool. However, it does not mention error cases, auth needs, or idempotency.

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

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

Extremely concise: two sentences and an Args list. Critical information (API key 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?

Adequate for a simple creation tool: explains purpose, key parameter roles, and a behavioral warning. Missing details like uniqueness constraints or error handling, but output schema may cover return values.

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

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

With 0% schema description coverage, the description adds minimal context by labeling the parameters 'Agent name' and 'Agent description'. This is better than nothing but not rich.

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 'Register a new remote agent' with a specific verb and resource. Includes a crucial caveat about the one-time API key display, which adds context beyond a basic description.

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

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

No guidance on when to use this tool versus alternatives like other agent-related tools. Does not mention context, 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?

No annotations provided, so the description carries full burden. It only says it returns a JSON string, but does not disclose side effects (e.g., whether the sender is notified), preconditions (e.g., request must be pending), or error scenarios.

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

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

The description is short and to the point, with a clear Args/Returns structure. No unnecessary words.

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

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

For a simple 1-parameter tool with an output schema, the description is adequate only in the most minimal sense. It lacks details on behavior, side effects, and error handling, leaving significant gaps for the 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 0%, and the description merely repeats the parameter name and marks it required. No additional meaning beyond the schema is provided.

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

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

The description clearly states the tool rejects a received contact request, using a specific verb and resource. It is distinct from sibling tools like approve_contact_request and cancel_contact_request.

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

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

No guidance on when to use this tool versus alternatives like cancel_contact_request, or when not to use it. No context about prerequisites or 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, the description carries the burden. It states the action is removal, requires permissions, and returns a success message. However, it does not address reversibility, errors, or side effects.

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

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

The description is concise with a clear first sentence, followed by permission note and structured Args/Returns. No unnecessary words.

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

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

For a simple removal tool with two required params and an output schema, the description covers permission requirements and return type. However, it could specify error conditions or the exact success message format.

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 the description's Args section adds semantic meaning: chat_id is 'unique identifier', participant_id is 'participant's ID to remove'. This significantly improves 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 tool removes a participant from a chat room, using a specific verb and resource. It differentiates from siblings like add_agent_chat_participant and remove_my_chat_participant.

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 mentions the acting agent must be owner or admin, providing a clear usage condition. However, it lacks explicit guidance on when not to use or alternatives.

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

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

No annotations provided, so the description carries full burden. It discloses key behaviors: removal by ID/handle, precedence rule when both provided, and return format. Could mention error cases or irreversibility but still 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?

The description is efficient: a one-line summary followed by detailed breakdown of parameters and return value. No extraneous content; every sentence contributes.

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 low complexity (2 optional params) and presence of output schema, the description covers core functionality, parameters, and return. Minor omission: no mention of error handling or assumptions.

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, so the description fully explains each parameter's purpose (contact_id as record ID, handle as handle) and the precedence rule, adding significant 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?

The description clearly states the tool removes an existing contact, specifies identification via contact_id or handle, and distinguishes it from sibling tools like remove_my_contact (which removes own contacts).

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

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

The description implies usage for agent contact removal but does not explicitly guide when to use this over alternatives like remove_my_contact. It lacks exclusions or contextual cues.

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

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

With no annotations, the description must disclose behavioral traits. It only states 'remove' without detailing side effects, reversibility, or permission requirements. This is insufficient for a mutation tool.

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

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

The description is extremely short but lacks critical information. It is concise but not structured to front-load essential usage context. Every sentence is earned, but more content is needed.

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 removal tool, the description minimally covers the action. The output schema exists and may cover return values, but no guidance on errors, success signals, or lifecycle impact is provided. Adequate but not complete.

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

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

The description repeats parameter names and required status already in the schema, adding no additional semantics. The 0% schema coverage means it does not compensate; parameters are self-explanatory but could benefit from format or source 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 it removes a participant from a chat room, specifying the action and resource. However, it does not differentiate from sibling tools like 'remove_agent_chat_participant', which may have different 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?

No guidance on when to use this tool versus alternatives, such as 'remove_agent_chat_participant'. No prerequisites or restrictions (e.g., ownership, permissions) are mentioned.

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

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

No annotations provided, so description must carry behavioral info. It states removal and returns JSON confirmation, but lacks details on side effects (e.g., does it affect chats?), permissions, or error scenarios. Adequate but not comprehensive.

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?

Description is concise with clear sentence structure, bullet-like listing of args, and return statement. Every sentence adds value with 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?

Given no schema descriptions and no annotations, the description covers purpose, parameters, and return. It lacks error handling or precondition details, but for a simple deletion tool, it is reasonably complete.

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

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

Schema has 0% description coverage with two nullable string params. Description adds crucial meaning: explains what each parameter is, optionality, at least one required, and precedence. This significantly aids correct invocation.

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

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

The description clearly states 'Remove an existing contact' and distinguishes from siblings like remove_agent_contact by specifying 'my' contact. The parameter details reinforce 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?

Provides clear guidance on when to use: to remove a contact by ID or handle, with precedence rules. However, no explicit 'when not to use' or alternatives are mentioned, though siblings like cancel_contact_request subtly hint at alternatives for pending requests.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the tool resolves a handle and returns details, which implies a read operation, but does not explicitly confirm no side effects, rate limits, or authentication requirements.

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

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

The description is concise, front-loaded with the main purpose, followed by a usage hint, and then parameter and return details. Every sentence adds value without waste.

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 tool with an output schema, the description covers the necessary information: what it does, when to use it, and what it returns. Slightly lacking in behavioral detail but sufficient for the agent.

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

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

The description adds meaning to the parameter 'handle' by labeling it as 'The handle to resolve' and noting it is required, which goes beyond the schema's title and type. With 0% schema description coverage, this is 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?

The description clearly states the tool resolves a handle to entity details, with specific verb 'resolve' and resource 'handle'. It distinguishes itself from sibling tools that focus on contacts, chats, and agents.

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 suggests using the tool to verify a handle exists before sending a contact request, providing clear context. Does not mention alternatives or when not to use, but the use case is well-defined.

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 the return value (JSON string confirming action) but does not disclose potential side effects (e.g., irreversibility), error conditions, or permission requirements. The behavioral disclosure is adequate but not rich.

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 well-structured with a lead sentence, bullet points for actions, and a clear Args/Returns section. It is concise, every sentence adds value, and it is easy to scan.

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 and the presence of an output schema (implied), the description covers the essential context: actions, identification, and return value. It lacks details on error handling or prerequisites, but for a contact request response tool, it is reasonably 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 0% schema description coverage, the description adds full meaning: action enums explained, handle and request_id described as optional identification fields, and the constraint that at least one must be provided. This fully compensates for the schema's lack of textual 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 it responds to contact requests with three specific actions (approve, reject, cancel), distinguishing it from sibling tools that handle only one action each. The verb 'respond to' combined with the resource 'agent contact request' is specific.

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 each action and how to identify the request (by handle or request_id). It does not explicitly exclude cases where sibling tools might be preferred, but it provides clear context for each action.

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

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

No annotations are present, and the description does not disclose behavioral traits beyond the basic action. It does not mention idempotency, required permissions, side effects, or what the output schema returns, leaving significant gaps.

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

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

The description is extremely concise: a single sentence followed by a clear args list with no redundancy. Every sentence adds value, and the format is front-loaded with the main action. 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 presence of an output schema (though not shown), the description does not need to explain return values. However, it lacks context about when to use this tool over other message-related tools (e.g., create_agent_chat_message). It also fails to clarify whether the message is sent to all chat participants or only those mentioned, leaving ambiguity.

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 effectively explains all three parameters. It adds meaningful constraints, especially for 'recipients' (non-empty, comma-separated, at least one name). For 'chat_id' and 'content', it provides basic context ('The chat room ID', 'Message text') that adds value beyond the schema's type-only definitions.

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

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

The description clearly states the tool's action: 'Send a message in a chat room.' It uses a specific verb and resource, making the purpose clear. However, it does not differentiate from sibling tools like create_agent_chat_message or list_my_chat_messages, which could cause confusion.

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

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

No guidance is provided on when to use this tool versus alternatives, such as when to send vs create a message. The description imposes a constraint on recipients (non-empty) but does not explain the intended context for this tool.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'Update', implying mutation, but does not mention side effects, permissions, validation, or return behavior. This is insufficient for a write operation.

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

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

The description is very short and front-loaded with the main purpose. Every sentence is necessary and there is 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?

Given the tool has only two optional parameters and an output schema exists, the description is minimally adequate but fails to explain update semantics (e.g., partial vs full replacement, what the output contains). Completeness is average.

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

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

Schema description coverage is 0%, so the description adds meaning by naming parameters and indicating they are optional. However, it does not provide constraints such as length limits or allowed values, leaving gaps.

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

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

The description clearly states the verb 'Update' and the resource 'current user's profile', making the purpose specific and distinguishable from siblings like get_my_profile.

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

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

No guidance is provided on when to use this tool versus alternatives (e.g., other profile update tools or user management tools). The description lacks any contextual direction.

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