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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: required scopes (agent.inbox.read, agent.read), agent-scoped bearer key requirement, prohibition on member/facility key impersonation, absence of image URLs/OCR trigger/retry/receipt, the untrusted-text warning, and the honesty expectation for null/queued/processing/failed/needs_review states.

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?

Front-loaded with the deprecation and successor, then ordered by operational concern (identity of the resource, key/scope, id semantics, verification, exclusions). It is long and dense, but nearly every clause carries distinct operational information; only minor tightening is possible.

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 not be described, and the description fully covers what remains: deprecation window, auth/scope preconditions, id provenance, status honesty, exclusions, and the untrusted-data caveat. Nothing an agent needs to invoke this correctly is missing.

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 100%, so baseline would be 3, but the description adds real semantics: request_id must be the REST operationId from list_agent_inbox_scans rather than a page or bundle ID. That disambiguates which id type is expected in a way the schema alone does not.

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 ('Read one exact completed facility capture and its saved page OCR'), names the exact endpoint path, and immediately flags deprecation with the successor get_inbound_pages. An agent can distinguish this from get_inbound_pages, list_agent_inbox_scans, and get_agent_inbox_activity without opening any 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?

Explicit routing in both directions: deprecated in favor of get_inbound_pages, use get_mailbox_md for full effective duties, do not acknowledge via report_agent_inbox_outcome. It also pins the correct id source ('Use request_id from list_agent_inbox_scans as the REST operationId, not a page or bundle ID'), which is exactly the when/how guidance an agent needs.

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