review_project

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 reveals the caching/sessionId behavior and the payload distinction between summary and full modes, which is genuinely useful. However, it doesn't disclose what the tool actually returns structurally, how long scanning takes, whether there are side effects, or what the 'health summary' contains — leaving significant behavioral ambiguity for an analysis tool.

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 and front-loaded, with the key action and workflow instruction in the first sentence. The second sentence is a useful conditional. Every sentence earns its place, though the term 'Analyze once' could arguably benefit from a more explicit rewrite.

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?

This is a moderately complex tool (3 params) with no annotations and no output schema, so the description must carry more weight. It explains the workflow and detail modes but omits what 'executive health summary' actually contains, what the sessionId is for beyond follow-up tools, and what counts as a valid project. Given the ambiguity of 'health' and the lack of disclosed output structure, more completeness would help agents 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?

Schema description coverage is 67%, so two of three parameters (detail, and path partially) are documented in the schema. The description adds context about the detail parameter's behavior (summary vs. full payload distinction) but doesn't explain the 'limit' parameter at all, which appears in the schema only as a bare max-300 integer with no description in the schema itself. With 67% coverage, the description partially compensates but leaves the 'limit' semantics unclear.

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 indicates the tool performs an analysis of a project, but uses opaque phrasing like 'executive health summary' without clarifying what 'health' means in this context. The name 'review_project' and the input schema's reference to 'Flutter/Dart project root' partially clarify the resource, but the description doesn't clearly distinguish this from sibling analysis tools like analyze_code_quality, analyze_architecture, or analyze_performance.

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 clear guidance on passing sessionId to follow-up tools to avoid rescanning, which is a useful workflow instruction. It also provides conditional guidance on when to use detail=full ('only when you need the entire report'). However, it doesn't explicitly contrast against the many sibling analysis tools or say when NOT to use this tool.

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