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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description goes well beyond that: it discloses a paywall, the exact 402/accepts[] failure mode with a retry protocol, and the identity precedence (guest token over account session). That is exactly the extra 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?

Four sentences, each doing distinct work: purpose, cost model, failure/retry path, and identity. Nothing is repeated or padded, and the purpose is front-loaded before the payment mechanics.

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 non-idempotent, paid mutation with no output schema, the description covers cost, auth identity, and the 402 recovery path, which is the information an agent needs to call it successfully. It never says what a successful response contains, a minor gap that keeps it from a 5.

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 100%, so body, author, and channel_id are already fully documented in the schema (including the max_length and stable-nickname behavior). The description adds no parameter-specific detail beyond what the schema states, 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?

The opening clause names a specific verb and resource ("Manda mensagem na sala de um canal por HTTP"), which clearly separates it from read-oriented siblings like chat_history and get_history. It stops short of naming an alternative explicitly (e.g. post_comment vs chat_send), so it lands at 4 rather than 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?

Strong operational guidance: reads are free while writes cost $0.10 per 30 days, an invalid pass yields 402 with accepts[], and the caller should pay and repeat the identical call. It also states who is speaking (X-Guest-Token guest, otherwise account session). It does not, however, contrast when to prefer this tool over post_comment or other siblings.

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