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

Annotations already declare read-only, idempotent and non-destructive, but the description adds substantial context beyond them: text is processed in memory and not stored, secrets are never returned in full (masked preview only), keys are never tested against providers, the 200,000-character cap, and format-based detection limits (a neutral-named random secret can be missed). It even discloses the return shape absent an output schema: severity tiers, line/column, why-it-matters, fix, revoke URL and a labeled redacted copy.

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?

Front-loaded with the usage trigger, then detection scope, then verification, then return values, then limits and privacy — a sensible priority order. It is delivered as one very long run-on paragraph, though, so the limits and the privacy fallback are easy to skim past; a sentence break for caveats would improve it.

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 two-parameter read tool with no output schema, the description covers everything an agent needs: what gets detected, what gets verified deterministically, what is returned (including severity and masked previews), hard limits, privacy behavior, and a fallback for the highest-sensitivity case. No meaningful gap remains.

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 baseline is 3, but the description adds real semantic context for the redaction toggle: the 'public' severity tier and the NEXT_PUBLIC_/VITE_/EXPO_PUBLIC_ variables that ship to browsers explain why public-by-design keys are treated differently from real secrets. It does not restate the parameter's default, but it supplies the reasoning an agent needs to decide whether to change it.

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 pair (detect and redact) against a specific resource (secrets/credentials in arbitrary text), and enumerates what counts as a secret (48 provider key formats, PEM private keys, DB URLs with passwords, JWTs, Authorization headers, high-entropy values in secret-named variables). Nothing in the sibling list overlaps with this, and the agent can tell instantly this is the credential-scanning tool.

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 explicit triggers ('did I leak a key in this?', 'is this safe to post?', 'redact the secrets in this log') and explicit moments to invoke proactively (before pasting, committing, sharing, logging or sending code, .env, diffs, config, logs, stack traces, prompts). It also names an alternative route for a case where this tool should not be used: secrets the user should not send anywhere go to the in-browser tool at spill.clawhard.com.

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