LMGram

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds no new behavioral context beyond 'Returns the profile', providing no extra transparency about side effects or authentication needs.

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

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

Single sentence that is front-loaded and contains no unnecessary words. Every word earns its place.

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

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

For a tool with no parameters and excellent annotations, the description is complete. It specifies the return value (LMGram profile) and context (connected account). No output schema needed.

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

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

No parameters exist, and schema coverage is 100%. Baseline for zero parameters is 4, as description doesn't need to add parameter meaning beyond the empty schema.

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

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

Description clearly states it returns the LMGram profile for the connected account, using a specific verb and resource. It is distinct from sibling tools that handle messages, matches, and 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?

No explicit guidance on when or when not to use this tool compared to siblings. The description is straightforward but lacks contextual usage advice.

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

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

Annotations already declare readOnlyHint and destructiveHint, so description adds 'current user' and 'recent' context. However, it omits details on ordering, pagination, or response format.

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

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

Single sentence is concise, but it omits critical details that would help the agent, making it under-informative rather than efficiently structured.

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

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

Given two parameters with no schema descriptions and no output schema, the description fails to explain the role filter, limit, or what 'match requests' entails, leaving significant gaps.

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

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

Schema has 0% description coverage, and the description does not mention the 'role' or 'limit' parameters, leaving agents to infer meaning from the schema alone.

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

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

Description clearly states 'lists recent match requests' for the current user, which is a specific verb and resource. It distinguishes from siblings like 'request_human_match' but could be more precise about what 'recent' means.

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 'request_human_match' or 'list_messages'. Does not mention that it is read-only (though annotations cover that).

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering safety profile. Description adds 'in a LMGram chat' but does not disclose return format, pagination, or other runtime behaviors.

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

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

The description is a single short sentence, which is concise but largely redundant with the title 'List chat messages'. It conveys the core purpose efficiently but adds no additional structure or 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?

With no output schema and one required parameter, the description omits important context like return format, ordering, or limits. For an agent to use this tool correctly, more details about the output and any constraints would be helpful.

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

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

Schema description coverage is 0%, and the description adds no meaning to the chatId parameter beyond its name. The parameter's role is implied by context, but the description does not explain format, constraints, or how to obtain valid chat IDs.

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 'Lists messages in a LMGram chat' uses a specific verb ('lists') and resource ('messages in a LMGram chat'), clearly distinguishing it from sibling tools like send_message and start_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?

No guidance on when to use this tool versus alternatives (e.g., when to use list_messages vs send_message for message operations). The description provides no 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?

The description adds the 'opt-in' and 'minimized session summary' constraints beyond the annotations. However, it does not detail side effects, authorization needs, or response behavior, and annotations already indicate it is a non-read-only, non-destructive 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 a single, efficient sentence that states the core action and key constraint. It is not verbose, but could be slightly expanded to include additional context without losing conciseness.

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

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

Given the tool has 8 parameters, 3 required, no output schema, and low schema coverage, the single-sentence description is insufficient. It omits return values, success criteria, and potential side effects, making it incomplete for a complex tool.

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

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

With only 38% schema description coverage, the description should compensate but only adds clarity for the 'summary' parameter (minimized, no secrets). Other parameters like 'need' and 'topic' rely entirely on their schema descriptions, which are present but not enriched by the tool description.

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 creates a human match request from a minimized session summary, using a specific verb and resource. However, it does not explicitly differentiate from sibling tools like start_chat or list_match_requests, 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, such as list_match_requests or start_chat. The description lacks context about prerequisites or typical use cases, limiting its utility for correct selection.

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

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

The description only states the basic action. It does not disclose behavioral traits such as side effects (e.g., notifications), error handling, or permissions required. Annotations provide readOnlyHint=false and destructiveHint=false, but the description adds no extra context.

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

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

The description is a single sentence, very concise, but it sacrifices completeness for brevity. It could include critical information without becoming overly long.

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

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

Given no output schema, no parameter descriptions, and simple structure, the description is incomplete. It does not explain return values, error conditions, or the relationship to sibling tools. The agent lacks sufficient information for correct invocation.

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

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

Schema has 2 parameters (body, chatId) with no descriptions (0% coverage). The tool description does not explain their meaning, format, or constraints. The agent must infer from parameter names alone, which may be ambiguous.

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 (sends) and resource (a message into a LMGram chat). It is specific but does not explicitly differentiate from sibling tools like list_messages or start_chat, though the verb and resource make the purpose evident.

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

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

No guidance on when to use this tool versus alternatives. No mention of prerequisites, cases where it should not be used, or comparison to siblings like start_chat or request_human_match.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description doesn't need to reiterate safety. The description adds that it 'records that this side wants to chat,' indicating a possible non-destructive side effect, but lacks details on idempotency (idempotentHint=false) or what happens on repeated calls.

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

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

The description is a single sentence that front-loads the primary action ('Starts a LMGram chat'). It is relatively concise, though the second clause could be rephrased for clarity without adding length.

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

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

Given the tool's low complexity (2 parameters, no nested objects), the description is arguably sufficient. However, it omits return value or side effects (e.g., whether the chat is instantly created or just requested), leaving some ambiguity. With no output schema, additional details would be helpful.

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

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

Schema coverage is 50%: 'body' has a description ('Optional first message'), but 'matchRequestId' lacks one. The description adds value by linking 'matchRequestId' to the match request context, though it does not provide syntax or constraints. This partially compensates 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 tool's function: starting a chat for a match request or recording intent. It uses specific verbs (start, record) and resource (LMGram chat, match request), and distinguishes from sibling tools like 'send_message' and 'request_human_match'.

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 a match request but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'send_message') or when not to use it. No prerequisites or exclusions are mentioned.

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