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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety basics are covered. The description adds substantial context the annotations cannot: cache-only, no provider contact, no background scan, every page has complete:false and snapshot:false, late-indexed messages can be missed, and cursor exhaustion does not prove history completeness. These are genuine behavioral disclosures, but a 3 reflects that much of the framing overlaps the readOnly/cache story already signalled structurally.

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?

The description is front-loaded with the core operation and the usage gate before the caveats, and every sentence carries distinct information about scope, alternatives, or incomplete-results risk. It is dense with semicolon-chained clauses, which costs a little readability, and the cursor-continuation sentence could merge with the exhaustion warning.

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 the description carries the return-value burden, and it does so precisely by enumerating the returned fields and stating what is absent (no subject, snippet, or body). For a paginated, eventually-inconsistent read tool it also covers the termination and completeness pitfalls an agent would otherwise misjudge.

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 75% and after, limit, and afterCursor are already documented, so the baseline is 3. The description nonetheless adds cursor-binding semantics ('Pass nextCursor unchanged to continue the requested scan'), which reinforces the schema's stability constraint in the context of a multi-page scan; it is slightly weakened by using 'nextCursor' while the parameter is named 'afterCursor', and accountId remains undefined in both description and 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?

The first sentence names a specific verb and resource — a bounded, cache-only page of mailbox metadata from a partial OpenSearch subset — and the final sentence scopes exactly what is returned. It explicitly distinguishes itself from list_mailbox_changes and implicitly from the live-fetch siblings by stating it never contacts a provider.

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 a narrow, explicit when-to-use condition ('only when CRM explicitly requests bootstrap or gap reconciliation'), an explicit when-not and alternative ('Use list_mailbox_changes for ongoing new arrivals'), and a procedural exclusion ('Do not restart automatically after exhaustion'). An agent has all routing information needed without inspecting the schema.

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