Scan for secrets

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description does add genuinely useful behavior beyond them: findings are masked to at most the first four characters, and each hit explains where and why. It says nothing about scan cost, latency, or limits on the number of findings, which for a whole-workspace scan would matter.

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 short sentences, front-loaded with the verb and scope, then the output shape, then the trigger. No repetition of the title and 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?

An output schema exists so return values need not be explained, and the description still gives the one detail an agent needs to interpret results safely (masked values, where/why per finding). Adequate for a zero-required-parameter read-only scan; only missing scan scale/cost context.

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% and there is only one optional boolean, so the schema carries the parameter meaning unaided; baseline 3 applies. The mention that saved examples are among the scanned surfaces implicitly signals why skip_examples exists, but the description never refers to the parameter directly.

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 (look for) plus the exact resource class (credentials) and enumerates the four surfaces scanned: requests, environments, scripts and saved examples. That scope is distinct from any sibling like lint_spec or list_requests, so the agent can choose it without opening the schema.

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?

"Run it before the developer commits or shares the workspace" gives a concrete trigger condition, which most definitions lack. It stops short of naming exclusions or alternatives (e.g. when not to bother, or what to pair it with), so it is clear context rather than a full selection rule.

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