fetch_inbox

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

Annotations only tell the agent it is not read-only and not idempotent; the description adds the crucial reason — mark_read defaults to true, so a call mutates read state — plus pagination semantics ('repeat only after a full page') and the filter-combination behavior. It does not spell out auth/permission needs or rate limits, so it falls just short of full disclosure.

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-loads the return shape before workflow guidance, and every sentence carries actionable content. The middle sentences are semicolon-dense and pack several defaults together, which costs a little readability, but there is no filler.

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?

For a 10-parameter tool with no output schema, the description covers return shape, ordering, defaults, pagination termination, mutation side effects, and routing to alternatives. An agent has everything needed to call it correctly without further lookup.

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 the baseline is 3, but the description adds meaning beyond the schema: it explains how defaults interact with the recommended workflow and that 'Filters combine, so omit optional filters when draining all unread mail'. That combination semantics is not stated in the schema itself.

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 ('Return an array of your latest received message metadata, newest first') with ordering and shape. It also names what the siblings do differently (search_messages for project-wide text matching, mark_message_read/acknowledge_message for a single message), so the agent can distinguish it 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?

Gives explicit when-to-use triggers ('At session start or after a mail notice, set unread_only:true, include_bodies:true and mark_read:true'), a stopping condition ('Stop when fewer than limit messages return'), and a metadata-preview alternative ('set mark_read:false'). It also names the sibling tools to use for other intents and states when to omit optional filters.

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