reply

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

Discloses key behaviors: immediate send (no queue/draft), consent-carrying, caller must be owner, reply lands in recipient's my_messages. With no annotations, it carries the burden well, though could mention rate limits or further auth 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?

Efficiently uses a few sentences to convey purpose, comparison, parameter details, and tier. Front-loaded with 'Answer a message.' Could be slightly more structured, but no 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?

Given the tool's complexity and lack of output schema, it explains the interaction with inbox/my_messages and the immediate nature. Missing error conditions, but overall sufficient for typical use.

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 meaning to 'to' and 'thread' (explaining source and threading). However, 'body' receives no additional description beyond the schema name, and schema coverage is 0%, so description only partially compensates.

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 'Answer a message' as the verb and resource, distinguishing it from sending new messages (sibling send_message) by emphasizing it as a reply. However, it does not explicitly differentiate from send_message, so it's not a 5.

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

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

Provides some guidelines: 'to' must be from inbox, 'thread' should echo the conversation. But lacks explicit when-to-use vs alternatives like send_message, and no when-not-to-use conditions.

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