verify_finding

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

With no annotations, the description must carry the behavioral disclosure. It does list the steps performed (reachability check, confounder elimination, CVSS calibration, PoC template generation) and states a requirement for CONFIRMED status. However, it does not disclose side effects (e.g., does it modify files?), what happens on failure, or any permissions required. It also doesn't mention whether the 'per-CWE PoC template' is written to disk or returned in the response. This is moderate disclosure, leaving important aspects implicit.

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 no filler. The first sentence front-loads the verb and object, then lists the actions in a compact list. The second sentence adds a critical prerequisite. Every word earns its place, and it is appropriately sized for the tool's complexity.

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's complexity (4 parameters, one a nested object) and no output schema, the description should explain what the tool returns or produces. It mentions generating a PoC template but does not specify whether that is returned as a string, written to a file, or included in the response. It also doesn't explain the possible outcome statuses beyond mentioning 'CONFIRMED' without elaboration. The description covers the process but not the result, leaving an agent uncertain about the tool's full behavior. It is adequate but incomplete for a tool this complex.

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 has 100% description coverage for all parameters, so the schema already documents each parameter (filePath, candidate, projectRoot, candidateJson). The description adds general context about the verification workflow (e.g., 'Requires high/medium confidence and cleared confounders') but does not provide parameter-specific semantics beyond what the schema offers. Satisfaction of prerequisites is mentioned, but it doesn't map directly to any parameter's format or usage. Since the schema covers the parameters well, the description's additional value is limited, meeting the baseline of 3.

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 a specific verb ('Verify a scan candidate') and lists distinct steps: reachability, 7-class confounder elimination, CVSS calibration, and per-CWE PoC template generation. This distinguishes it from sibling tools like check_reachability, calculate_cvss, and generate_poc, which each handle only one of these aspects.

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 provides clear context: this tool is for verifying a scan candidate through a multi-step process. It includes a prerequisite for achieving CONFIRMED status (high/medium confidence and cleared confounders), which guides usage. However, it does not explicitly state when to use this tool instead of calling the individual sibling tools (e.g., 'use this instead of separate calls to check_reachability, calculate_cvss, etc.'), so it lacks explicit exclusions or alternatives.

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