Explain the scan in plain English

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

Goes well beyond the annotations by disclosing the external dependency (CODE_GUARDIAN_LLM_URL), the data egress boundary (findings only, no source), that the score is not modified, and the degradation path (returns a note without a model). These are exactly the behavioral traits an agent cannot get from readOnlyHint/idempotentHint.

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?

Three tight sentences, front-loaded with the core action and followed by the two constraints that matter (what is sent, what happens without a model). No filler.

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?

With no output schema, the description still conveys the return shape (plain-English summary, or a note when no model is configured) and the safe-read nature. Minor gap: it doesn't hint at summary length/format or latency from the model call.

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% with only 2 params, so the schema already carries the parameter semantics (including the goal-contract default). The description adds no parameter-level detail, so baseline 3 applies.

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+resource: it runs the scan and asks a local model for a plain-English summary of the findings. This implicitly distinguishes it from the sibling `scan` (raw scan output vs. narrated explanation), though it never names the sibling 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?

Usage is implied rather than stated: an agent can infer this is the 'explain the scan' path versus the plain `scan` sibling, but there is no explicit when-to-use/when-not or named alternative. Adequate but leaves selection logic to inference.

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