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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description goes well beyond this by stating that no acknowledgment version or extraction is created, no ETag/cursor/export is promised, no receipt or charge is generated, pagination is a current view rather than a snapshot, and scoped agent keys are required. There is no contradiction with annotations.

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 deprecation and purpose, but it is very long and packs in many security, retry, pagination, and exclusion caveats. While most sentences carry useful information, it is not concise and could benefit from tighter organization.

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 output schema exists and the tool is complex, the description is remarkably complete. It covers deprecation, purpose, authentication, pagination behavior, performance guidance, retry semantics, exclusions, and points to outputSchema for field meanings and sort order. Nothing essential 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 description coverage is 0%, so the description must compensate. It explains limit/offset ranges and defaults, notes that sources use has_more with offset plus returned length, and refers to 'item_id pages.' It does not explicitly define item_id as the inbound-item identifier, but the context is sufficient for correct invocation.

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 opens with 'Deprecated: use get_inbound_item' and then states it is the 'Primary OCR read after list_agent_inbox: GET /v1/agent-inbox/:id/sources.' This gives a specific verb, resource, and endpoint, while explicitly pointing to the replacement sibling. The purpose is unambiguous and differentiated from related tools.

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?

It explicitly says to use get_inbound_item instead, frames this tool as a legacy alias, and provides strong operational guidance: use after list_agent_inbox, narrow queries/date windows, fetch selected items, and avoid polling every mailbox. It also identifies exclusions like managed-PMB custody and forwarded email.

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