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

Annotations already declare idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds valuable behavioral context: the lease mechanism, the need to keep runId and leaseToken, the renewal requirement, and the meaning of the two refusal responses. It doesn't contradict annotations. It doesn't detail what happens if the lease expires beyond the claim being offered to someone else, but that is already stated. A 4 is appropriate because it adds meaningful behavioral context beyond the 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 a single dense paragraph that front-loads the most important instruction ('Call this the moment you begin executing a task — BEFORE doing the actual work'). It covers the lease, renewal, refusals, and next step without wasted words. Slightly long but every sentence earns its place.

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 single-parameter tool with no output schema, the description is quite complete: it explains the lease, the return values (runId and leaseToken), the renewal cadence, the two expected refusals, and the follow-up call. It doesn't describe the exact response format, but no output schema exists and the key return values are named. A 4 is fair.

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% and the only parameter (id) is described as 'Task ID' in the schema. The description doesn't add much beyond that, but with a single required UUID parameter, the schema is sufficient. Baseline 3 is correct.

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 states a specific verb ('Call this the moment you begin executing a task'), a specific resource (the task being claimed), and a clear action (claims the task with a lease, moves it to Doing, starts cycle-time tracking). It clearly distinguishes itself from siblings like complete_task and report_progress by naming them and describing the workflow.

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?

The description explicitly says when to call it ('the moment you begin executing a task — BEFORE doing the actual work'), what to do after (call report_progress at least every renewEverySeconds), and what to do when finished (call complete_task). It also explains two expected refusal responses and how to handle them, which is strong usage guidance.

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