finish_work

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

With no annotations, the description carries full burden. It usefully discloses persistence ('kept with the claim (/work/<claim>/)') and downstream consumption ('what the next agent is shown'), which are real behavioral facts. It omits auth/permission needs (api_key) and any notion of reversibility or side effects on other claims.

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?

Front-loaded with the core action, then scope, then payload guidance. Four compact clauses with little waste; the parenthetical about /work/<claim>/ is slightly awkward but earns its place by explaining retention.

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 9-param, mutation-style tool with no annotations and no output schema, the description covers the lifecycle and most payload fields but leaves two parameters (api_key, agent) undocumented and says nothing about authorization or error behavior.

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?

9 parameters with 0% schema coverage, so the description must compensate. It gives meaning for result, status (enumerating done|dropped, which the schema lacks), claim_id (empty = all open claims), and the code-artifact fields (repo, branch, commit, diff). It leaves api_key and agent completely unexplained.

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 (close) + resource (work claim) with scope qualification (all open ones when claim_id is empty). This clearly distinguishes it from the sibling start_work and the subtask/claim lifecycle tools.

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?

Explains the triggering condition (closing a work claim), what to supply as the result, the allowed status values, and when to attach code identifiers. It does not name an alternative tool or state exclusions, so it stops short of a 5.

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