check_redaction

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

With no annotations, the description carries the full burden and it excels. It discloses that most redaction tools leave characters in the file, explains what surfaces are checked (text layer, under redaction marks, incremental revisions, metadata, AcroForm fields, attachments), states that processing is on-device ('the raw value never leaves the machine'), and details the free-tier cap and evaluation-marked reports. This is exemplary transparency beyond what any annotation could provide.

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 front-loaded with a clear one-sentence summary, then expands into rationale, checks performed, output type, limitations, and free-tier behavior. Every sentence adds value—no filler. Despite being long, it is well-organized and earns its length through density of useful information.

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 complexity (multiple scan surfaces, output report, free-tier cap, limitations) and the lack of annotations, the description is exceptionally complete. It covers the input, process, output ('coverage report'), failure interpretation ('non-empty result means the redaction leaked'), and usage constraints. The presence of an output schema reduces the need to detail return fields, and the description sufficiently complements it.

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%: the single parameter pdfPath is described as 'absolute path to the supposedly-redacted PDF to audit.' The description reinforces that the PDF must be 'ALREADY-redacted' but adds no new syntax or format constraints beyond the schema. Baseline 3 applies because the schema already covers the parameter adequately.

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 first sentence clearly states the tool's purpose: 'Audit an ALREADY-redacted PDF and report whether sensitive text still survives underneath the redaction.' It uses a specific verb ('Audit') and resource ('ALREADY-redacted PDF'), and differentiates from siblings by focusing on the post-redaction verification step, even calling it 'the did my black boxes actually remove the data?' check.

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 implies when to use the tool: after redaction, to verify data removal. It also provides explicit limitations ('Pattern-based: names/addresses, image-only text, and the surfaces listed as not-inspected aren't covered; absence of hits isn't proof of completeness'), which helps an agent decide if this tool is appropriate. However, it does not explicitly name alternative sibling tools or state when NOT to use this tool in favor of another, so it falls just short of a 5.

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