run_checks

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

With no annotations, the description carries the full burden and does substantial work: it discloses the default discovery behavior (no specs → glob verify_*.py under project), the shape of the returned JSON report, and the full status vocabulary (PASS, EXACT, FAIL, INCONCLUSIVE, ERROR, SKIP), which tells an agent that failures are reported per check rather than raised. It does not disclose that checks execute user simulation code (side effects, runtime cost) or any permission prerequisites, leaving a real gap for an execution 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?

Front-loaded with the action and its check families, then invocation, then return shape — a sensible order with no filler sentences. The final enumeration is long but earns its place because no output schema exists. Slightly dense as a single paragraph.

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 3-optional-parameter execution tool with no annotations and no output schema, the definition covers purpose, default resolution, and the returned report fields well enough to invoke correctly. What is missing is behavioral risk framing around running simulation code and whether timeout aborts mid-family, but that is a narrow gap rather than a blocking one.

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 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: it explains that `specs` contain definitions of checks(), and crucially explains the fallback interaction — omitting specs triggers a verify_*.py search under `project`. That relationship between two optional parameters is not inferable from the schema alone.

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: runs physverify verification checks (manufactured solutions, order of convergence, invariants, limits, exactness) on physics simulation code, and names the input artifact type (spec files defining checks()). This is far more specific than the name alone. It offers no explicit contrast with its sibling confirm_claim, so it falls just short of 5.

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 makes the invocation mode clear: pass spec files, or omit them and let it discover verify_*.py under `project`. That is usage-adjacent guidance but it never states when to prefer this tool over an alternative or when it would be inappropriate (e.g., non-physics code, very long runs). Usage context is implied rather than prescribed.

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