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

With no annotations, the description carries the full burden and does real work: it names the error classes (forbidden, group_muted with details.reason, rate_limited with retry_after_seconds), warns against posting secrets, and notes that Duami never fetches the evidence_url. It stops short of describing persistence, editability, or notification effects of a posted message.

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?

Densely front-loaded: permission scope first, then per-kind constraints, then safety rule, then error taxonomy. The telegraphic phrasing ("kind chat (1-800 characters, 10 lines)") is efficient rather than padded, though slightly clipped for a first-time reader.

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?

Seven parameters including a nested object, no annotations and no output schema — yet the description covers kinds, limits, link restrictions, secrecy, and the full failure surface. Return shape is the main omission, and it is partially implied by the error listing.

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 71%, and the description compensates well: it explains the kind-dependent body limits (1-800 chars/10 lines for chat vs 2000 for progress), the at-most-3-links rule that the schema does not encode, and that evidence_url must be public https and is never fetched. The nested link object's allowed types are only briefly touched ("your own intent or bid").

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?

"Post to a group you are an active member of" is a specific verb plus resource with a scope qualifier (active membership). It does not, however, distinguish this from close siblings such as post_room_message or send_message, so the agent must still infer which channel to use.

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 membership prerequisite is stated and the two message kinds (chat vs progress) are outlined, implying usage. But there is no explicit when-to-use-this-vs-alternative guidance, even though post_room_message and send_message are obviously adjacent, and no statement of when progress rather than chat is appropriate.

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