set_task_state

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

Discloses behavioral traits: no lease extension, claim stays visible as held-but-stuck, fails with 409 if claim inactive, and 'Hosted API only' constraint. No annotations to contradict.

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?

Concise, 4 sentences with no fluff. Front-loaded with core purpose. Every sentence adds value.

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?

Complete given no output schema: explains purpose, states, error condition, and downstream visibility. Adequate for successful invocation.

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 has 100% coverage with descriptions. The description adds context for the detail parameter (examples like 'needs prod API key'), reinforcing usage beyond the schema.

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 tool reports the session state of a claimed task (working, waiting_input, errored) without extending the lease. This is specific and distinguishes it from siblings like heartbeat_task.

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 says when to use (flag blocked on input or error) and implies not to use for normal progress (alternatives like heartbeat). Also notes failure with 409 if no active claim.

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