scan_code

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

With no annotations, the description carries the full burden and does well: it discloses the mechanism (regex, hence no semantic understanding), the accuracy profile ('false positives and misses expected'), and the speed trade-off ('Fast'). It omits operational details such as output shape, severity scoring, or the 200k character input cap, which is why it isn't a 5.

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?

Two tight sentences: capability first, then the honest limitation caveat. Every clause earns its place — the vulnerability list and the heuristic disclaimer are both load-bearing.

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 tool with no annotations and no output schema, the description explains what it detects and how much to trust it, but leaves two gaps: it never explains what a scan returns (finding list, severity, line refs?) and never documents its two parameters, one of which is 0%-covered by the schema.

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 0% and the description never mentions either parameter. 'Snippet' loosely implies the required `code` argument, but `filename` and the 200,000-character maxLength constraint are completely undocumented in both schema and description, so an agent gets no guidance on what `filename` changes (language detection? path-based context?).

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?

States a specific verb and resource ('fast regex review of a snippet') and enumerates the vulnerability classes it targets, which makes its purpose unmistakable. The word 'snippet' implicitly separates it from the path-based sibling scan_path, but it never names that sibling explicitly, so the differentiation is inferred rather than stated.

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?

Gives clear contextual guidance: it 'complements SAST, never replaces it', which tells the agent this is a supplementary heuristic pass rather than an authoritative audit. It stops short of explicit routing rules — nothing says when to prefer scan_path, secure_coding_checklist, or search_security over this tool.

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