find_sensitive_data

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: control-digit validation for IBANs, cards and register numbers, and the fact that returned values are masked. It does not mention performance or file-format limits.

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 detected data types and followed by validation and masking behavior. No filler, though the first sentence could have stated scope (whole document vs. page range) more explicitly.

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-value documentation is unnecessary. However, with a required 'path' and an optional 'kinds' parameter completely undocumented, an agent lacks the information needed to invoke the tool correctly, leaving a real completeness gap.

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% for two parameters. The description never mentions the 'path' argument or the 'kinds' selector, so it does not compensate for the schema gap. The list of detectable kinds hints at what 'kinds' might accept but gives no syntax or allowed values.

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 (Find) and resource (sensitive data) and enumerates the exact patterns detected: IBANs, card numbers, national register numbers, VAT numbers, e-mails, phone numbers, birth dates. The purpose is unmistakable and clearly distinct from read_text or redact, though no sibling is named 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 use case is implied by the enumeration of detectable data types, but there is no explicit guidance on when to use this versus alternatives like redact (which acts on such data) or read_text. No prerequisites or exclusions are stated.

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