Diagnóstico de escáneres

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

readOnlyHint=true already tells the agent this is a safe read, so the description's job is lighter. It adds real content beyond the annotation by disclosing the three things returned: availability, version, and execution origin of each scanner. It does not describe the result shape (e.g., per-scanner status codes or error reporting for missing scanners), which is the remaining gap.

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?

A single sentence, front-loaded with the action and immediately followed by the enumerated scanners and the returned attributes. Nothing is redundant or padded.

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?

For a zero-parameter, read-only diagnostic with no output schema, listing what is reported (availability, version, origin) is close to sufficient. What is missing is follow-up guidance for the negative outcome — what an agent should do when a scanner is absent — which is the main remaining incompleteness.

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 tool takes no parameters, so the schema imposes no semantic burden and the baseline of 4 applies. The description correctly implies the check runs across all supported scanners with no user-supplied scope, which is consistent with the empty input object.

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?

Specific verb ("Revisa") plus a precisely scoped resource: which scanners are available, their version, and where they execute from. The enumeration of concrete scanners (Semgrep, Bandit, CodeQL, OSV-Scanner, Trivy, Gitleaks, Nuclei) makes it obvious this is a diagnostic check rather than a scan, distinguishing it from the scan_* siblings. It stops short of naming a sibling to route away from, which keeps it at 4.

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?

Usage is only implied: an agent can infer it should call this to verify scanner availability (e.g., before scan_static or scan_iac). There is no explicit when-to-use, no when-not, and no pointer to alternatives such as xolotl_install for the case where a scanner is reported missing.

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