inbox_done

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

The description states 'deletes their downloaded copies,' which is a destructive action, but the annotations declare destructiveHint: false. This is a direct contradiction. The additional note about TTL recovery does not reconcile the mismatch, so the behavioral information is misleading.

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?

Three sentences, each earning its place. The main action is front-loaded, followed by a usage condition and a recovery note. There is no fluff or redundant information.

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?

The description covers purpose, precondition, parameter shape, and persistence behavior (TTL). It provides enough detail for an agent to invoke the tool correctly, even without an output schema, and the only significant gap is the annotation contradiction which is already flagged.

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?

The schema only defines 'keys' as an array of objects with additionalProperties: true. The description adds essential semantics: 'Each key is {"chat_id": int, "message_id": int}. This precisely specifies the required structure, compensating fully for the 0% schema coverage.

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 clearly states the action: 'Mark messages as archived, which deletes their downloaded copies.' It uses a specific verb and resource, and the context about buffer copy redundancy distinguishes it from sibling tools like inbox_fetch or inbox_export.

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 'Call this only after the messages are in the archive with their hashes' and explains why (the buffer copy is redundant and grows on disk). This provides a clear precondition and rationale, effectively telling the agent when to use this tool.

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