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

Annotations already give the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true); the description adds real value beyond them by disclosing the privacy contract ('no person and nothing that was said') and that 'nothing public changes by itself'. It also links an authoritative how-to doc. It stops short of explaining retry/duplicate handling explicitly, which idempotentHint partly covers.

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?

Three front-loaded sentences: trigger first, then the outcome vocabulary and cap, then the privacy constraint and doc link. Dense but nearly every clause carries information; the run-on semicolon listing of result values is the one spot that costs readability.

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?

An output schema exists, so return values need no prose; what an agent still needs — when to call, valid outcome values, batch limit, privacy restrictions, and a pointer to the full spec for the nested report object — is all present. Adequately complete for a batched write tool.

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 reported as 0% at the top level, so the description has to compensate — it does meaningfully: it defines the result vocabulary with parentheticals ('invalid (your own request's fault)', 'info (needs a person)'), states the 100-item batching cap, and constrains payload content for privacy. It never explains the required 'v' version field, and it says 'failed' where the schema enum value is 'fail', a small mismatch.

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?

Specific verb + resource: 'After you used a business's door ... record how it went', and it enumerates what a 'door' is (inbox, MCP, A2A, API). No sibling tool records post-call outcomes (ask_business, request_booking, room_* are all interaction/registration tools), so the name/description are unambiguous against the sibling list.

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 trigger condition is explicit — call this after using a door — and batching guidance is given ('up to 100 uses a call'). It doesn't state any when-not-to-use case (e.g. don't report doors you merely discovered but never called), which is the only gap.

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