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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds real behavioral value beyond that: the 201-on-new-send / 200-on-Idempotency-Key-replay response contract. The only tension is that this replay semantics reads as idempotent while idempotentHint=false; the description is defensible because the key is optional, but it is worth noting.

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 short sentences with no filler, and the status-code contract is front-loaded after the purpose line. It is efficiently sized, though its brevity is partly a symptom of under-specification rather than disciplined economy.

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 the success path's status codes but omits anything about failure modes (recipientUnavailable, profileAmbiguous, contentRejected are only in schema sub-descriptions), rate limits, or thread-creation behavior. For a mutating send with no output schema, this is adequate but leaves 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 description coverage is only 50% across 4 parameters, and the description explains none of them (target, content, idempotencyKey, replyToMessageId). A tool where half the parameters are undocumented in the schema needs the description to compensate, and this one does not.

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 opens with 'Send message,' which is a specific verb+resource, but it is a verbatim restatement of the title rather than an elaboration of what is being sent or where. It does nothing to distinguish this tool from messages_edit, messages_unsend, or threads_typing, leaving the agent to infer the boundary from names alone.

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?

There is no when-to-use guidance, no prerequisites, and no named alternatives. The agent is given no signal about when to send via a thread target vs. a contact target vs. a profile target, nor when to prefer messages_send over messages_edit.

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