send_claim_message

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

No annotations exist, so the description carries the full burden and does so well: it discloses that the message is REAL and visible to both buyer and Mercado Livre mediation, that it becomes part of the claim record, that text must be user-confirmed, and that the moderation rules (no contacts, links, phone, e-mail) carry sanction risk. It even states the return shape (message id and date).

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?

Front-loaded with the core action, then prerequisites and risk in descending priority. Slightly redundant — the moderation constraint is repeated in both prose and the 'text' schema description — but every sentence otherwise carries operational weight.

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?

Covers the prerequisite tool, the visibility/irreversibility risk, the compliance constraint, and the return payload, with no output schema needed. An agent has everything required to invoke this correctly and safely.

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 both parameters (text, claim_id) are already documented, including the moderation constraint and the claim_id source. The description adds no syntax, format, or length semantics beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb+resource+actor: 'Send a message inside a claim (reclamação) thread as the seller.' This is clearly distinct in kind from the generic send_message sibling, though the description never explicitly names that sibling to contrast with it.

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?

Explicit prerequisite and ordering: 'Use get_claim_detail first to read the thread context.' It also gives the when-to-be-careful condition (confirm exact text before sending). It stops short of naming send_message as the non-claim alternative, which would make routing fully unambiguous.

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