axiom_audit

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

No annotations exist, so the description carries the burden. It reveals that the tool compares `#print axioms` output against an allowlist and that it is designed to catch `sorryAx`. It does not disclose behavior on mismatch, effect (read-only vs write), or handling of the optional `allowed` parameter.

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?

Two sentences, front-loaded with the core action, and the second sentence provides valuable motivation without excessive detail. Every sentence earns its place.

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?

The description is sufficient to understand the tool's overall purpose but is incomplete for invoking it correctly: the `allowed` parameter is never precisely defined, and there is no information about return values or failure signaling. For a two-parameter tool with no annotations or output schema, more detail is expected.

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?

The description adds the 'allowlist' concept, which maps to the `allowed` parameter that lacks a schema description, but it doesn't specify the expected string format or how violations are reported. The `output` parameter is already described in the schema, so the description adds little there. With 50% schema coverage, the description only partially compensates.

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 ('Audit `#print axioms` output against an allowlist') and ties it to a concrete failure mode (`sorryAx`), making the tool's role clear. It does not explicitly compare with siblings like lean_check or evidence_audit, so it doesn't fully earn the top score.

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 provides context for when this check matters (a clean compile with `sorry` exits 0), implying use when you need to ensure no `sorry` axioms appear. It does not name alternative tools or state when not to use it, leaving the decision partially to inference.

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