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

Annotations already mark idempotent and destructive, and the description adds crucial context: acking twice is harmless, a late redelivered ack still succeeds because there is no fence token, unknown task_ids return acked:false, repeating schedules queue the next occurrence, and the result is persisted on a tombstone. 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 dense but every sentence carries a distinct fact: idempotence, rescheduling, tombstone, late-ack behavior, unknown-task response, pricing, authentication, and HTTP route. It is front-loaded with the core purpose before edge cases.

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 destructive, no-fence ack operation with no output schema, the description covers the necessary operational context: side effects, error behavior, authentication, cost, and the key alternative. An agent has enough to decide whether to call it and what to expect in the failure case.

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 schema already documents all four parameters. The description adds meaning beyond the schema by explaining that the result is stored on the tombstone for later duplicates and that agent_key is only a fallback for hosts that cannot set the Authorization header.

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 and resource — 'Acknowledge a task you finished' — and reinforces the scope with the title 'Mark a task done'. It also disambiguates from fenced alternatives by explicitly naming work_take/work_done for refuse-on-lost-ownership, making sibling differentiation clear.

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 tells the agent when to ack and when not to: ack finished tasks promptly, raise visibility_timeout_seconds on inbox_poll if needed, and switch to work_take/work_done when fenced refuse-on-lost-ownership is required. This explicitly covers a when-not case and an alternative tool.

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