reply

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

Annotations provide destructiveHint=true, but the description adds crucial behavioral details beyond that: idempotency behavior (with idempotencyKey or body hash), the fact it sends from the mailbox that sent the thread, and the 404 error scenario. No contradictions with annotations.

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

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

The description is four sentences, front-loading the primary purpose, then inputs/output, idempotency details, and error case. Every sentence earns its place; no fluff or 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 output schema, the description mentions return format ({ messageId }), covers idempotency and error. For a 3-parameter tool with no nested objects, it provides sufficient context for an agent to use correctly, though it omits rate limits or auth requirements.

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

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

Schema description coverage is 67% (threadId and idempotencyKey described, body not). The description adds context by stating 'from the mailbox that sent it' (implied parameter) and explains idempotencyKey fallback to body hash. This adds semantic value beyond schema 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 'Send a reply on an existing thread', specifying the verb (send), resource (reply on thread), and context (from the mailbox that sent it). It distinguishes from siblings like 'thread' (retrieve thread) and 'mark' (mark status) by focusing on reply action.

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

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

The description explicitly details when to use this tool (to reply to an existing thread) and notes a critical error condition (404 if no sending mailbox on record). However, it does not provide explicit when-not-to-use guidance or compare against specific sibling alternatives like 'thread' or 'mark'.

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