Scan a repository or directory

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

Annotations already declare readOnlyHint=true, so the description adds valuable behavioral traits: 'fast, offline, deterministic' and 'returns findings sorted by severity.' These go beyond the annotation and help the agent anticipate behavior. No contradiction.

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 compact and front-loaded: it starts with the action, then lists detection targets, and ends with performance and output traits. Every sentence earns its place; no fluff or repetition.

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 simplicity (one parameter, no output schema), the description covers the core behavior and mentions output sorting. It doesn't detail the finding structure, but sibling tools like explain_finding likely cover that. The description is sufficient for an agent to call the tool correctly.

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 100% for the single parameter, so the schema fully documents the 'path' parameter. The description adds no extra parameter-level detail beyond confirming it's a filesystem path, which matches the schema. Baseline 3 is appropriate.

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 states a specific verb ('runs'), a concrete resource ('Kelp's static engine over a filesystem path'), and enumerates exactly what it detects (hardcoded secrets, Supabase edge functions, etc.). It clearly distinguishes from siblings by the 'path' scope, even though it doesn't name alternatives explicitly.

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 makes it clear that this tool scans a filesystem path and what it finds, but it does not explicitly state when to prefer this over scan_snippet or when not to use it. The usage is implied but not contrasted with alternatives.

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