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

Goes well beyond the annotations by disclosing a hard rate limit (maximum three follow-ups per request), an optimistic-concurrency requirement (current revision), an audience constraint, and the failure mode ('a changed room fails closed'). The annotations only say destructive/not-idempotent/open-world; the description adds the operational rules an agent must respect. A required idempotency_key alongside idempotentHint=false is a nuance worth noting, but the description's retry-key language makes the intended retry behavior clear rather than contradicting it.

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?

Five short sentences with no filler, purpose front-loaded first, then prerequisites, limits, and failure behavior. Every sentence carries a distinct constraint an agent needs before calling.

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?

No output schema exists, so return values need not be explained, and the description covers prerequisites, cap, and failure mode for a guarded mutation. It leaves minor gaps: what happens when the three-follow-up cap is exceeded, and how the required connection credential interacts with private calls in practice.

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 80%, so the schema already documents most parameters, and the description largely restates them ('current revision', 'retry key'). It adds a small amount of semantic weight by implying revision guards against concurrent changes rather than being a version label, but there is no format or failure-of-validation detail beyond the schema.

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 and resource — sending a follow-up — and pins the scope to 'this request's existing room,' which separates it from generic message_send and from request_retry. The follow-up semantics plus the three-message cap make its niche distinguishable without opening any sibling schema.

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?

Gives explicit when-not conditions: stop when the request is blocked, cancelled or no longer useful, read history first, and no automatic nagging. It does not, however, name an alternative tool (e.g. request_retry or request_get) for the cases where a follow-up is the wrong move, which is what a 5 would require.

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