start_work

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

No annotations are provided, so the description carries the full burden. It usefully discloses the status semantics, the ownership window ('yours until finish_work or handoff'), force/reason semantics, and that `related` lists connected memories - but it never mentions auth (api_key), what persistence/claiming actually happens, or race/conflict behavior, leaving meaningful behavioral gaps for a state-changing tool.

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?

Dense and front-loaded ('Before ANY task...'), with a branch structure that earns its space. Slightly cluttered notation (backtick references, terse branch fragments) and the bare `related` reference add minor ambiguity, but little is wasted.

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 annotations, no output schema, and 0% param coverage across 7 params, the description must carry everything. It adequately covers the coordination flow and statuses but omits the return shape, auth/project/agent parameter meaning, and any conflict/race handling, so an agent still has unresolved questions before calling it.

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 coverage is 0% across 7 parameters, so the description must compensate. It explains the semantics of force, reason, and paths, but leaves what, agent, api_key, and project entirely undocumented, covering only about half the parameters that actually need explanation.

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 clear action (check a task against other agents' live/finished work before starting) and routes ownership via status branches, and it names siblings finish_work and handoff implicitly to define scope. It is distinguishable from those siblings, though the core 'claim/start' action is conveyed indirectly through the 'ok = yours until finish_work' phrasing rather than stated outright.

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 'Before ANY task' and gives when-to-use/when-not branching: busy = don't start, done = build on it only with force=true + reason for a real follow-up. It names the alternative and the exact condition that selects each path, leaving little to inference.

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