Scan text for risky agent instructions

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

With no annotations, the description carries the burden. It discloses key behaviors: runs locally, no network, no collector dependency, and returns structured findings (severity, title, explanation, evidence). However, it does not mention potential side effects or timeouts, and the return format (list of findings) is partially described but not exhaustive. It does not contradict annotations, so a 3 is appropriate.

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 concise and front-loaded: it states the purpose in the first clause, then adds key differentiators (local, no collector) and the output format. Every sentence adds value, with no filler or repetition. It is well-structured for quick comprehension.

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 moderate complexity (two params, no output schema), the description covers the main usage: what it scans, how it runs, and what it returns. It omits details like error handling, length limits (though schema has maxLength), or performance characteristics, but the essential information for correct invocation is present. It's slightly incomplete because the return format isn't fully specified (e.g., exact structure of findings), but that is not critical.

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 coverage is 100%, so the schema already documents both parameters (kind and content). The description adds the meaning of 'kind' by referencing 'agent skill/instruction file or MCP server config,' which is a slight elaboration, but it doesn't add syntax or format details beyond the schema. Baseline 3 is correct.

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 the tool performs a heuristic risk scan on inline text, specifying two content types (skill/instruction file or MCP config). It distinguishes from siblings like beam_scan_path, which presumably scans a file path, by emphasizing 'inline text.' The verb 'scan' and resource are specific, leaving no ambiguity.

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 implies when to use by focusing on inline text, implicitly contrasting with beam_scan_path (likely path-based). It clearly states local execution and that the collector doesn't need to run, which is a usage condition. However, it does not explicitly mention when NOT to use it (e.g., for file paths) or list alternatives, so it's slightly below a 5.

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