Verify Intent

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

Beyond the readOnlyHint annotation, the description discloses that it never raises on failing invariants, returns failures as passed=False rows, and is safe for repeated calls. It also states it is inspection-only and composes lower-level checks, giving the agent accurate expectations for side effects and error behavior.

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 compact, front-loaded with purpose and usage, and each subsequent sentence adds either behavioral nuance or return-format detail. No filler or redundant restatement of the tool name.

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 one-parameter read-only verification tool with no output schema, the description fully documents the return dict fields, invariant names, failure semantics, and prerequisite. An agent has enough information to call the tool correctly and interpret results.

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?

With schema description coverage at 0%, the description compensates by explaining that handle refers to the part and must have a declared intent contract. It ties the parameter directly to the tool's operation, though it could add a bit more detail about handle format or examples.

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 specific action ('Re-run every invariant declared with declare_intent') and a clear resource (declared invariants for a part). It differentiates the tool from related siblings by naming its composed checks (check_shape / check_airtight_path / face-role resolution) and its relationship to declare_intent.

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?

It explicitly frames the tool as the regression gate to run after each edit and notes that it is safe to call in a loop. It does not name alternative tools or give when-not-to-use exclusions, but the intended usage context is clear.

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