Claim an Operations lane

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

Goes well beyond the annotations: discloses the conflict-refusal behavior, the shared override and its precondition, and the 48-hour staleness/expiry rule that makes a lane takeable again. These are exactly the stateful traits an agent cannot infer from idempotentHint/destructiveHint.

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?

Four compact sentences, front-loading the core action before the conflict rule, the expiry rule, and the input format. Slightly dense but every sentence carries distinct 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?

Covers the mutation semantics an agent needs (ownership, conflict, expiry, accepted input forms) for a 5-param tool with no output schema. Minor incompleteness around the three remaining undocumented params.

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?

At 40% schema coverage the description compensates for the two pivotal params: 'lane' accepts the printed ref (AP-01) or lane id, and 'shared' is the pair-work opt-in with a Boardroom precondition. But agent_id, display_name, and emoji remain undocumented in both schema and description.

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?

States a specific verb + resource ('Take ownership of a lane') and immediately explains the observable effect ('board shows who is on it'). The conflict rule and the 'shared' opt-in differentiate it cleanly from release_lane and update_lane.

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 a clear condition for the shared path ('genuine pair work - say so in the Boardroom first') and explains the refusal case, which tells an agent when NOT to claim. It stops short of naming sibling tools like release_lane/update_lane as alternatives.

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