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.

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

With no annotations provided, the description carries the full burden and does well: it discloses on-device rendering, that it writes the PDF, returns the path, and that nothing is uploaded. It could be even more explicit about overwrite behavior or error handling, but core side effects and privacy are covered.

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?

Four sentences and front-loaded with purpose. The phrase 'not like a script's best guess' is charming but non-essential; still, the description is compact and readable.

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 PDF-generation tool with a rich schema and output schema, the description covers input modes, privacy, output destination, and alternative tooling. It does not describe failure scenarios or path validation, but that is acceptable at this complexity level.

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?

Input schema covers all 6 parameters with descriptions (100% coverage), so the baseline is 3. The description lightly reinforces roles of source, sourcePath, and outputPath, but adds no new meaning beyond schema for css, title, or format.

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 description opens with a specific verb ('Generate'), names the resource ('PDF'), and specifies input formats (Markdown or raw HTML). It also distinguishes from sibling redaction/verification tools by clearly positioning this as a PDF creation 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?

The description explicitly says 'Use this instead of writing a one-off reportlab/LaTeX/pandoc script,' giving clear guidance on when to prefer it. It also tells the user exactly how to invoke it: provide source/sourcePath and outputPath.

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

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

With no annotations provided, the description carries full burden and fully delivers: it discloses local/on-device processing, no upload, masked previews, best-effort/no-guarantee nature, check-digit validation, CRN format-only, and free-tier cap behavior with EVALUATION-marked results. This is a comprehensive transparency disclosure.

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 purpose and is well-structured, but it is long and contains slight redundancy (e.g., 'never uploaded' and 'secret stays on the machine'). Still, every sentence contributes meaningful information for a complex tool.

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 (free-tier cap, security, coordinates, PII types) and the existence of an output schema, the description is complete: it covers behavior, limitations, security, and workflow. It does not need to explain return values because the output schema exists.

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 covers both parameters with descriptions (100% coverage), so baseline is 3. The description adds value by explaining how to use regions ('select regions by entity') and that coordinates are directly usable by redact_pdf, providing semantic context beyond the schema, though it does not add new parameter-level details.

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 description states the tool scans a PDF and returns candidate PII regions with page and coordinates, and explicitly contrasts it with redact_pdf ('Use this FIRST... instead of guessing geometry from a rendered page'). This identifies the verb, resource, and output, and distinguishes it from siblings like locate_text and redact_pdf.

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 gives explicit workflow guidance: use this tool first to select regions by entity, then pass coordinates to redact_pdf. It also clarifies the free-tier cap and structured refusal, and notes that plaintext is not needed. This clearly communicates when and how to use the tool versus alternatives.

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

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It discloses case-insensitivity, the split-text-operator limitation, the masked-preview output ('not the raw text'), and the privacy guarantee ('Nothing is uploaded'). This is exemplary transparency beyond what any schema could convey.

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 the core purpose and each sentence adds distinct value: purpose, usage guidance, behavioral caveats, output format, and privacy. It is appropriately sized for the tool's complexity without redundancy or 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?

The description is fully self-contained for a two-parameter tool. It explains what the tool returns, how to use it effectively, important edge-case caveats, and privacy behavior. An output schema exists to describe the return structure, so the description does not need to list return fields.

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?

The input schema already describes both parameters completely (pdfPath and texts with descriptions), so the baseline is 3. The description reinforces that texts are 'literal strings' and that matching is exact, but it does not add substantial new parameter-level detail. The schema does the heavy lifting here.

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 description opens with a specific verb and resource: 'Locate exact text strings in a PDF and return each occurrence's page and coordinates (in PDF points).' It clearly distinguishes from siblings by framing it as the exact-match counterpart to pattern-matching tools. This makes the tool's purpose immediately unambiguous.

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?

Explicit guidance is given: 'Use this for what pattern-matching can't catch' and the user is told to do entity recognition themselves and pass literal strings. It also names the downstream workflow: 'Feed the returned regions straight to redact_pdf.' This provides clear when-to-use context and an implicit alternative (pattern-matching).

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

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

No annotations are provided, so the description carries the full burden. It discloses that processing is on-device, matches are best-effort pattern matching (not a completeness guarantee or compliance assessment), returns what was redacted plus an audit log, and that nothing is uploaded. This is rich, non-obvious behavioral context.

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?

Two sentences deliver all essential information: purpose, usage flow, alternatives, caveats, and privacy/upload behavior. The opening is front-loaded with the core action, and every clause earns its place without redundancy.

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 an output schema present, the description still explains what is returned ('what was redacted plus the audit log') and handles the tool's complexity: entity kinds, omit-all behavior, regional packs, review flow, and limitations. This is fully complete for a 5-param tool.

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 baseline is 3. The description adds meaningful semantics beyond the schema: 'omit `kinds` to redact every kind detected' clarifies default behavior, and 'regions narrow to these regional packs (intersects with `kinds`)' explains the relationship between params. This rises above baseline.

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 description uses a specific verb+resource: 'Find and redact PII in a PDF in ONE on-device step' and clearly distinguishes this from sibling tools by framing it as the 'just scrub the obvious PII' shortcut. It explicitly contrasts with find_sensitive_regions, which is a strong differentiator.

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 states when to use this tool ('shortcut' for scrubbing obvious PII) and explicitly names an alternative: 'when you need to review before removing, call find_sensitive_regions first.' It also mentions the same caveat as the detector, giving clear context for suitability.

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

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

With no annotations provided, the description fully discloses key behavioral traits: permanent destruction of underlying data, self-verification, signed audit log, and local processing. It clearly conveys that this is a destructive, privacy-preserving operation, going beyond what annotations would typically 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 three concise sentences, front-loaded with the core action. Each sentence adds value: what it does, how it works, and the privacy benefit. No fluff or redundancy.

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?

The description is largely complete for a tool with a rich output schema (signed audit log) and no annotations. It covers major behavioral aspects and privacy. However, it doesn't address potential ambiguity with sibling tools like verify_redaction or check_redaction, leaving a small gap in understanding when to use this tool versus those verification tools.

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?

The input schema covers all parameters (100% coverage), so the description does not need to add much. It mentions 'regions' and 'on-device' but does not provide additional detail beyond schema descriptions. The schema already explains coordinate system, page indexing, and required fields.

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 description clearly states the tool's purpose with a specific verb ('redact'), resource ('PDF'), and scope ('regions'). It also distinguishes from siblings like redact_by_entity by emphasizing region-based redaction versus entity-based.

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 gives clear context for when to use the tool (on-device, region-specific redaction) but does not explicitly mention alternatives or exclusions. It implies usage through the focus on 'regions' and 'on-device,' which differentiates it from sibling tools like redact_by_entity or verify_redaction.

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

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

With no annotations, the description carries the full burden and excels: it discloses the two distinct execution paths, prerequisites (native engine + sidecar), fallback behavior, and the explicit caveat that the fallback is 'a good-faith re-check, not a claim of the same rigor.' It also notes 'on-device' operation, adding meaningful privacy context.

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 two well-structured sentences that pack substantial information without waste. The em-dash and parenthetical structure breaks the sidecar and fallback modes cleanly, and every clause adds value. No redundancy with schema or sibling names.

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 (two modes, prerequisites, caveats), the description covers all essential context: what it verifies, the strongest path, fallback behavior, and the rigor limitation. An output schema exists, so return values don't need explaining. This is complete for an AI agent to use correctly.

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 a clear description for pdfPath ('absolute path to the redacted PDF to verify'). The tool description adds context about sidecars and modes but doesn't elaborate on the parameter itself beyond the schema. Baseline 3 is appropriate since the schema already handles parameter semantics fully.

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 description opens with a specific verb+resource: 'Re-scan an already-redacted PDF on-device and confirm nothing recoverable remains.' It clearly distinguishes the tool from siblings by introducing the sidecar-based rigorous path vs. the fallback general re-scan, making its scope and intent unmistakable.

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 provides clear usage context: use with a configured native engine and the file's sidecar for the strongest check, and falls back to a general re-scan otherwise. It explains when each mode applies, but doesn't explicitly name alternative tools like check_redaction or state exclusions, so it stops short of a full 5.

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

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It reveals key traits: on-device processing (nothing uploaded), the integrity-not-identity caveat, the requirement for a configured native engine, and the meaning of an unsupported version verdict. These go beyond basic expectations and significantly inform the agent of operational constraints and limitations.

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 a single dense paragraph but every sentence contributes value. It front-loads the main purpose, then adds distinguishing, caveats, requirements, and verdict handling. While it could be broken into shorter paragraphs for readability, it is not wasteful and maintains focus.

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 cryptographic verification tool with important nuances, the description is remarkably complete. It covers the exact object of verification, the distinction from a sibling, the integrity vs. identity trap, the need for a native engine, and the interpretation of a special verdict. Since an output schema exists, return values are presumably defined there, so the description covers all necessary contextual ground.

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?

The input schema already fully describes the sole parameter (`pdfPath` as absolute path), achieving 100% coverage. The description does not add further semantic detail about the parameter itself, only contextual background about the file's contents. Thus, the baseline score of 3 is appropriate.

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 description clearly states the tool's specific purpose: verifying a PDF's embedded Omitly audit report and trailing Ed25519 tamper-evidence seal. It distinguishes itself from the sibling `verify_redaction` by explicitly contrasting their functions, making the tool's role unambiguous.

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?

It provides explicit guidance on when to use this tool vs. verify_redaction, explaining the difference in what each checks. It also gives critical direction on how to handle identity verification (comparing sealFingerprint out-of-band) and what to do upon receiving a `seal_unsupported_version` verdict (update verifier, not trust/reject). This fully addresses usage context and alternatives.

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