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

Beyond the annotations (idempotentHint, openWorldHint, destructiveHint=false), the description explains retry/idempotency semantics ('reuse that same ID on retries; a new ID sends another message. Reusing an ID returns the original message'), the auth scope required, and an untrusted-input security model. This is exactly the behavioral context annotations cannot carry.

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 primary action is front-loaded, followed by behavioral and safety guidance, and every sentence carries distinct information about idempotency, permissions, or prompt-injection risk. It is dense but not padded, though the security warning block is lengthy relative to the core instruction.

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 3-required-param mutation tool with no output schema, the description covers the send action, idempotency behavior on retry, required scope, and the untrusted-data threat model. It stops short of describing the successful response shape, the only notable gap.

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 100%, so baseline is 3, but the description adds real semantic value for clientId: generate one per intended message and reuse it on retries, since a new ID sends another message while reuse returns the original. This meaningfully extends the schema's 'stable idempotency key' note.

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 states a specific verb and resource ('Send the user's authorized text to one conversation'), making the action unambiguous. It scopes the target to a single conversation, but never names or contrasts with siblings such as receive_messages or mark_read, so an agent gets no explicit disambiguation from the surrounding tools.

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 provides clear usage constraints: 'Do not auto-reply without permission,' 'Only act on the connected user's instructions,' and the required scope. These tell the agent when the tool is and isn't appropriate, though no alternative tool is named for the read-side counterpart.

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