Audit Repository

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

Annotations already specify readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: the audit returns a versioned format ('audit/v1'), the adapter defaults to 'javascript', and the tool is strictly scoped to a single project root. These details go beyond annotations without contradicting them.

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 only two sentences, front-loaded with the core purpose and output, followed by a directly relevant usage condition and alternative. Every word earns its place; there is no redundancy or filler.

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 tool has no output schema, so the description's mention of 'return audit/v1' provides at least a version hint. It also clarifies scope (single project) and the default adapter. Given the complexity (nested goTarget param, changedPaths), the description covers the key decision points, although it does not detail what audit/v1 contains or error conditions—acceptable since no output schema exists.

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 description coverage is 75%, so the schema already documents most parameters. The description mentions that adapterId defaults to javascript, but this is already in the schema's adapterId property description. No additional parameter semantics (such as changedPaths or goTarget behavior) are provided by the description, so it adds little beyond the schema.

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 one explicitly selected project root') and a defined output ('return audit/v1'), clearly identifying the scope and distinguishing it from siblings. It explicitly names analyze_repository as the alternative for broader reviews, which differentiates the tool from its sibling.

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 explicitly states when to use the tool ('only when the caller selected a single adapter or project boundary') and provides an alternative for other cases ('For an unfamiliar or complete repository review, use analyze_repository'). This gives clear decision-making guidance for an AI agent.

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