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

Annotations already declare non-readonly, idempotent, non-destructive, closed-world, but the description adds critical context they cannot: the not_live failure semantics, the 404-not-403 cross-org behavior, and the explicit guarantee that no completion/receipt is produced. This is exactly the extra behavioral disclosure annotations cannot carry.

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?

Extremely dense and front-loaded: lease-extension purpose first, then failure semantics, then guarantees, then auth, then error codes. No sentence is 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?

With no output schema, the description fully compensates by describing the success/failure signal ('ok false with reason not_live') and the 404 case, plus the auth scope. An agent has everything needed to call this correctly and interpret the result.

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 description coverage is 100%, so run_id, instance, and extend_seconds are already fully documented in the schema, including the same-instance mismatch behavior and the never-shortens lease rule. The description adds no parameter meaning beyond that, so the baseline of 3 applies.

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?

Specific verb+resource with scope: 'Extend a claimed local run's lease and mark it running', plus the underlying endpoint mapping. An agent can distinguish it from tascan_claim_run and tascan_finish_run purely from the text.

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-not behavior ('ok false with reason not_live ... STOP, do not finish it') and an explicit prerequisite ('Requires agent:dispatch:code'). It also bounds the tool's role by stating it never mints a completion or receipt, which routes completion work elsewhere.

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