project_audit

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

With no annotations, the description carries full burden. It explains the tool is a read-only audit that returns verdicts and findings, and advises on marker emission. It does not disclose any destructive behavior; the tool appears non-modifying. Transparency is good but could be more explicit about side effects.

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 reasonably concise with two sentences, but the first sentence is lengthy with internal lists. It is well-structured: purpose, method, returns, and guidance. Minor verbosity does not detract significantly.

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 simple input (one optional parameter), no output schema, and no annotations, the description fully covers the tool's purpose, inputs, outputs (verdicts with evidence and findings with fixes), and usage advice. No gaps are evident.

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 sole parameter 'root' is fully described in the schema (100% coverage). The description does not add meaning beyond what the schema already provides, so baseline 3 is appropriate.

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 audits implementation against design contract for drift detection, specifies the static tiers (screen registry and markers), and describes return values. It distinguishes itself from sibling tools like project_init or screen_critique by focusing on compliance verification.

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 gives explicit guidance on when to use the tool: when implementing screens from the contract, emit markers to keep code self-auditing. It also implies usage for drift detection but does not explicitly state when not to use it or provide alternatives, though sibling tools offer context.

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