verify_work

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It lists the types of checks (sanity, test, git diff, architecture) but does not state whether the tool is read-only, whether it modifies the workspace or task state, what side effects running tests might have, or what a 'reality verification dossier' contains. This lack of safety and side-effect information is a significant gap.

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 sentence that front-loads the verb and the key checks. It is concise and to the point, though the phrase 'reality verification dossier' is somewhat jargon-heavy. Every word contributes to the purpose, and it is not overwritten.

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?

Given the tool's complexity (multiple check types), lack of annotations, and many similar siblings, the description is incomplete. It does not explain when to use this tool over alternatives, does not define the path parameter, and leaves behavioral side effects unspecified. The existence of an output schema mitigates the need to describe return values, but the other gaps remain critical.

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 for both parameters. It implicitly ties task_id to the task being verified, but the 'path' parameter is completely unexplained. The description doesn't clarify what path refers to (e.g., project root, source directory) or how it interacts with task_id. Without this, an agent cannot correctly set path.

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 clearly states the tool's purpose: performing deep sanity, test, git diff, and architecture checks against a task to produce a verification dossier. This is a specific verb ('perform') and resource ('task'), and the combination of check types distinguishes it from sibling tools like validate_architecture or verify_requirements. However, it does not explicitly name these sibling tools, so it stops short of full differentiation.

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 offers no guidance on when to use this tool versus alternatives. It neither states explicit use cases nor mentions exclusions (e.g., 'for code-only checks use validate_architecture'). With numerous sibling verification tools (verify_outcome, verify_requirements, compare_work_to_prd), an agent would be unsure which one to select for a given task.

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