start_work

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: a side effect (board sync moves the card to In Progress) and an error outcome (stale token yields stale_claim). It omits permission requirements, idempotency, and what happens if the task is not in 'claimed' state.

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?

Three sentences, each earning its place: the transition, the side effect, the failure mode. The core action is front-loaded with no 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?

For a mutation tool with no annotations and no output schema, the description covers the transition, its board side effect, and one error. It leaves the as_agent parameter and any indication of what a successful call returns or how to detect success undocumented.

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 0%, so the description must compensate. It explains ClaimToken well (must be the original, stale tokens fail), but the 'as_agent' parameter is never mentioned and no value format for ClaimToken is given.

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 and resource plus the exact state transition ('claimed' to 'in_progress'), which cleanly separates it from siblings like claim_next_task, mark_task_status and release_claim. An agent can identify the tool without opening the schema.

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 precondition is implied by 'a claimed task' and 'requires the original claim token', which tells the agent it must have claimed work first. However, it never names the alternatives (mark_task_status, release_claim, refresh_claim) or states when NOT to use it, so routing is left partly to inference.

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