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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: the tool is deprecated but still served unchanged during the alias window, text is untrusted document data never instructions, captures are separate from seeded sample /context and have no context_version, and required scopes are listed. It also warns against substituting another key or mail API after denial. This goes beyond annotations without contradicting them.

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 a dense wall of caveats, deprecation warnings, security notes, and exclusions. While each sentence carries information, the core purpose is front-loaded but the rest is unstructured and overwhelming. It reads as a list of warnings rather than a coherent tool description, and several points (rollout switches, SQL authorization) are tangential for an agent deciding whether to call the tool.

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?

Given the tool's complexity, the deprecation status, and the presence of an output schema, the description covers the critical operational context: how to map the operationId, what to verify in the response, what not to do, and required scopes. The output schema presumably documents return values, so the description doesn't need to. The main gap is the unexplained item_id parameter, but overall the description is quite complete for a deprecated read 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 0%, so the description must compensate. It does explain that request_id is the REST operationId from list_agent_inbox_scans, not a page or bundle ID, which adds meaning to that parameter. However, item_id is not explained at all beyond the schema's UUID format, and the description doesn't clarify the relationship between item_id and request_id. With 0% schema coverage, the description partially compensates but leaves a gap.

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 description states a specific verb and resource: read one exact completed facility capture and its saved page OCR via a REST endpoint. It also names the replacement tool (get_inbound_item) and clarifies the operationId mapping. However, the description is heavily overloaded with deprecation and caveats, and the core purpose is somewhat buried; it doesn't clearly distinguish from get_agent_inbox_activity or get_agent_inbox_context beyond the deprecation note.

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 description explicitly says 'Deprecated: use get_inbound_item' and provides clear when-to-use guidance: use request_id from list_agent_inbox_scans as the REST operationId, not a page or bundle ID. It also gives exclusions: do not acknowledge with report_agent_inbox_outcome, no image URLs, OCR trigger, retry, receipt, email or charge. This is strong routing and usage guidance.

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