inbox_fetch

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

Discloses the side effect of marking messages as taken, consistent with readOnlyHint=false and idempotentHint=false. Clarifies non-destructive behavior ('Fetching does not remove anything') and adds forwarded-message origin context. Slight gap: no mention of error conditions, but the key behavioral traits are covered.

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?

Four sentences, front-loaded with purpose, then critical details. No filler; each sentence earns its place. The structure logically progresses from core action to workflow to recovery use case.

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?

Covers the main workflow, time-range semantics, and recovery scenario. Has an output schema, so return values need no explanation. Missing explicit guidance on chat and limit parameters, but these are relatively self-explanatory from the schema names.

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?

With 0% schema coverage, the description must compensate. It explains since/until as ISO-8601 UTC timestamps and include_taken's purpose. However, chat and limit are left undescribed; limit may be inferred as a count, but chat's role is only implicit from the message context.

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 a specific verb+resource: 'Fetch buffered messages for a time range and mark them as taken.' This clearly states the tool's function and distinguishes it from siblings like inbox_done (archive/completion) and inbox_status.

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?

Explicitly directs the workflow: 'call inbox_done once the messages are recorded in the archive.' Also explains the include_taken flag as a recovery mechanism for interrupted batches. This provides clear when-to-use and when-not-to-use guidance.

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