find_eval_sites

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

With no annotations, the description must carry the behavioral burden, but it only adds the word 'heuristic' to indicate non-exhaustive detection. It does not disclose whether the tool is read-only, how results are returned, or any limitations or side effects, leaving significant behavioral ambiguity.

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 very short and front-loaded, but it is a fragment rather than a complete sentence. While every word is meaningful, the truncated structure and lack of punctuation make it less clear than it could be; it balances conciseness with under-specification.

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?

With no output schema, the description should explain what a result looks like (e.g., a list of code locations), but it does not. It also omits any mention of prerequisites like a loaded project. While the tool is simple, the missing return-value and context information leaves notable gaps.

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 schema already covers the only parameter ('name') with a description, and the tool description adds no parameter-specific information. Since schema coverage is 100%, a baseline of 3 is appropriate; there is nothing to penalize or reward beyond that.

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 names the specific resource ('eval / new Function / Function()') and indicates the tool is a heuristic scan, making its purpose clear. However, it lacks an explicit verb like 'finds' and reads more as a noun phrase, so it doesn't fully meet the specificity of a full sentence. It does distinguish from sibling tools focused on other patterns (SQL injection, XSS, etc.).

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?

No guidance is provided about when to use this tool versus alternatives like find_xss_vectors or find_command_injection. The description does not state any context or prerequisites (e.g., that a project must be loaded), so the agent must infer usage from the tool name and schema.

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