audit_instructions

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only; does not rewrite files' and clarifies that it produces 'advisory keyword risk summaries' rather than enforcement. This is valuable beyond the raw schema and gives an agent essential safety expectations, though it could go further (e.g., whether scanning is recursive) if that information were relevant.

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 two sentences, with the first sentence front-loading the core scope and the second sentence adding essential behavioral clarifications. Every clause earns its place; there is no redundant or filler wording.

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 has only one optional parameter, an existing output schema, and a read-only, non-destructive nature, the description is complete. It explains what is audited, the categories of analysis, the read-only guarantee, and what the tool is not for, leaving no significant gap for an agent to select or invoke it correctly.

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 input schema already documents the single `path` parameter thoroughly with a description and default behavior, achieving 100% schema description coverage. The tool description does not add additional parameter-level semantics beyond reinforcing the resource being audited ('instruction files'), so the baseline of 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 opens with a specific verb ('Audit') and a clear resource ('local agent instruction files'), then enumerates precise audit dimensions: exact same-file duplicates, cross-file surface overlap, and advisory keyword risk summaries. It also distinguishes itself from siblings by explicitly excluding semantic drift and safety enforcement, making its purpose unambiguous.

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 states when to use the tool: to audit local agent instruction files for duplicates, overlap, and keyword risks. It also gives exclusions ('is not semantic drift or safety enforcement') and emphasizes read-only behavior, which helps an agent avoid invoking it for rewrite tasks. However, it does not explicitly recommend alternative sibling tools for those excluded use cases, so it stops short of full alternative guidance.

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