send_message

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

With no annotations at all, the description does state the main side effect (a message is posted to a thread as the calling agent) and two hard constraints (size cap, server-only kind). However, it does not mention whether the send is durable, how subscribers/visibility are affected, error conditions, permission requirements, or whether sending is idempotent.

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 compact: two sentences that state the core action immediately and surface the most critical constraints. There is no filler or repetition.

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 16 parameters, no annotations, and no output schema or error semantics, a two-sentence description is not sufficient for an agent to confidently use all capabilities. The cap and kind restriction are useful, but key behaviors around enums like authority, trust_class, and visibility remain unexplained.

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?

Given only ~2 of 16 parameters are meaningfully documented by the schema, the description adds semantic value only for body size routing and kind='system'. Fields like authority, trust_class, visibility, deadline_at, requires_ack, and refs are left largely unexplained in the description, so the agent must guess at their effect.

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 names a precise action ('Post a MESSAGE to a THREAD'), identifies the agent as the caller, and clearly distinguishes this from sibling tools like create_thread or record_structured_result. The intent is immediately unambiguous.

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 gives an explicit routing rule: messages over 16 KiB should go to record_structured_result with a refs pointer, and kind='system' is server-only. It does not contrast with other sibling tools or state when to prefer one kind/authority over another, but the key alternative is covered.

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