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

With no annotations provided, the description bears full burden for behavioral disclosure. It states it runs all audits and returns a consolidated result, but does not disclose whether it modifies the project, permission requirements, or performance implications. While not misleading, it lacks details that would help an agent assess risks or side effects.

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 sentences: one clearly stating functionality, one providing usage guidance. No redundant words, front-loaded with the core action. Every sentence earns its place.

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?

While the schema covers parameters and the description states purpose, the tool is an aggregate that runs multiple sub-audits. The output format is only vaguely described as 'consolidated result'. Given no output schema, the description could clarify the structure (e.g., list of individual audit results) to help the agent process the response. Adequate but not complete.

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%, so baseline is 3. The description does not add any information about parameters beyond what the schema already provides (projectRoot as absolute path, allowlists as per-language overrides). No additional semantic clarity from the description.

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 runs every AADC compliance audit and returns a consolidated result, using specific verb 'run' and resource 'AADC compliance audits'. It distinguishes itself from sibling individual audit tools (e.g., aadc.audit_defaults) by being the aggregate version.

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 states when to use: 'whenever the user asks for a full AADC review of a kids app, or before a store submission.' This provides clear context and implicitly directs users to sibling tools for specific audits.

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?

The description indicates a 'warn-only scan' implying non-destructive behavior, but with no annotations, more detail would be beneficial—e.g., what gets scanned, performance impact, or result handling.

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?

Single sentence with key information front-loaded. Very concise, though the term 'Standard 7' may be obscure.

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?

Adequately describes the tool's scope and non-destructive nature, but lacks explanation of 'Standard 7' and expected output format, which could hinder effective use.

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%, so the baseline is 3. The description adds no additional meaning to the parameters beyond what the schema already provides.

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 a specific verb ('scan') and resource ('default-true on suspicious privacy keys'), and distinguishes from siblings by referencing 'Standard 7' and a heuristic warn-only approach.

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?

No guidance on when to use this tool versus sibling audits like aadc.audit_all or aadc.audit_permissions. The description lacks explicit context for usage or 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, the description only states it flags URLs but does not disclose behavioral traits such as whether it modifies files, requires authentication, or what the output format is. Missing context on side effects or error conditions.

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 extremely concise (two sentences) and front-loads the core purpose. Every sentence is essential with 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?

Given no output schema, no annotations, and nested objects in params, the description lacks completeness. It does not explain the return values, how standards 4 and 6 are applied, or provide examples, leaving the agent underinformed for correct invocation.

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%, and the description does not add additional meaning beyond what is already in the input schema. The description does not elaborate on the parameters, so it meets baseline but does not enhance understanding.

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 it flags hardcoded URLs outside the CMS that bypass content review, and references specific standards (4, 6). This distinguishes it from other audit siblings like aadc.audit_launchurl or aadc.audit_permissions.

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 usage for detecting hardcoded URLs bypassing CMS review, but does not explicitly state when to use or not use this tool vs alternatives like aadc.audit_all or aadc.audit_link_reachability.

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 must carry full burden. It states the purpose but does not disclose behavioral traits such as read-only nature, required permissions, error conditions, or return behavior. For an audit tool, these are important contextual hints.

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?

Single sentence efficiently conveys purpose and standards. No fluff, front-loaded with key action ('audit') and resource ('Dart launchUrl() calls').

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?

Description explains the audit target and constraints but does not describe the output format (e.g., list of violations, pass/fail). No output schema exists, so the description should provide some expectation of results. References to standards 11 and 14 are unelaborated.

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% (both parameters have descriptions in the schema). The tool description adds no additional parameter meaning beyond what the schema already provides, so baseline 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 audits Dart launchUrl() calls for safe-link helper usage and external browser path restrictions. It references specific standards (11 and 14), distinguishing it from sibling audit tools by specifying a focused scope.

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 the tool is used when auditing launchUrl calls for compliance with standards 11 and 14, but does not explicitly state when to use it versus alternatives like aadc.audit_all or aadc.audit_hardcoded_url. No when-not-to-use guidance is provided.

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 must convey all behavioral traits. It states it is 'warn-only,' implying no destructive action, but lacks details on network access requirements, error handling for unreachable links, or what constitutes a warning. Missing context on how 'Standards 4, 6' affect behavior.

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 concise sentence that front-loads the key behavior ('Warn-only check'). However, the mention of 'Standards 4, 6' may be unclear without expanding on what those standards entail. No unnecessary words.

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 low complexity (2 optional parameters, no required params) and presence of sibling audit tools, the description provides the core purpose but lacks details about the output format and how results are returned. Since there is no output schema, the description should at least hint at the return value (e.g., list of dead links).

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%, so the baseline is 3. The description adds no additional parameter information beyond what the schema already provides. The schema itself describes projectRoot and allowlists 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 description clearly states the tool performs a 'warn-only check' for 'external links referenced in content are reachable and not dead.' It references 'Standards 4, 6,' which provides additional context but is somewhat cryptic. The purpose is distinct from sibling audit tools, though it does not explicitly differentiate.

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?

No guidance on when to use this tool versus other audit tools like aadc.audit_all or aadc.audit_hardcoded_url. The description does not mention prerequisites, when not to use it, or alternatives. The 'warn-only' hint is the only usage insight.

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 bears full responsibility for behavioral disclosure. It only states the audit action without detailing side effects, permissions, or output, leaving significant gaps.

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?

Description is a single sentence, very concise but lacks necessary details. It front-loads the purpose but is too brief to be fully informative.

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 absence of annotations and output schema, the description should provide more context. It fails to explain the audit process, the role of allowlists, or what the output represents, making it incomplete.

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 descriptions for both parameters. The tool description adds no additional meaning beyond the schema; it only mentions Standard 8 which does not relate to parameters.

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?

Description clearly states it audits protected paths (microphone, camera, on-device-only data) for network API imports and mentions Standard 8. However, it does not distinguish from sibling audit tools like aadc.audit_all or aadc.audit_defaults.

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?

No guidance on when to use this tool versus alternatives. The description lacks context on when to apply this audit or when not to, leaving the agent without decision support.

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?

The description states the tool audits for permissions outside an allowlist, implying a read-only operation. With no annotations provided, the description carries the full burden, but it lacks details on error handling, file existence assumptions, or side effects. It is minimally adequate.

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 sentence that conveys the core purpose and scope. It is concise and front-loaded, but could be slightly more structured without adding length.

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 tool has two optional parameters and no output schema. The description explains the input files and allowlist concept but does not describe return values or error handling. It is adequate for a simple audit tool but lacks completeness for an agent to fully understand behavior.

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 both parameters adequately described in the schema. The description does not add extra meaning beyond what the schema provides, so a 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 identifies the tool's purpose: auditing native iOS Info.plist and Android AndroidManifest.xml for permissions outside an allowlist. It also references standards 8 and 10. However, it does not explicitly differentiate from sibling audit tools, though the specific file types provide some distinction.

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 does not provide guidance on when to use this tool versus other audit tools (e.g., audit_all, audit_defaults). No when-not-to-use or alternative suggestions are given. The agent would need to infer usage from the tool's specific focus on permissions.

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 must fully disclose behavioral traits. It mentions scanning in 'shipped user-facing strings' but does not clarify if the tool is read-only, destructive, or any side effects. The description lacks details on behavior beyond the scan action.

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 concise sentence that covers the core purpose. It is front-loaded and direct, though it could benefit from a slight structure like listing the placeholders checked.

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 has 2 parameters (including a nested object) and no output schema, the description should explain what the tool returns or how to interpret results. It does not mention output format, error conditions, or help for the allowlists parameter, leaving gaps for an agent.

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%, so the schema already documents both parameters. The description adds no additional meaning beyond what is in the schema. Baseline 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 scans for unreplaced placeholder content like lorem ipsum, TODO copy, and dummy text, and references standards 4 and 6. However, it does not explicitly differentiate from sibling tools like audit_all or audit_defaults.

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 no guidance on when to use this tool versus alternatives, no exclusions, and no context about prerequisites or typical use cases. It only states what it does, not when to use it.

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?

The description states it is a 'Warn-only check', which indicates non-destructive behavior. However, with no annotations provided, it fails to disclose other behavioral traits such as what happens if the policy is missing, how SDK dependencies are detected, or any side effects.

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?

A single, concise sentence that clearly conveys the tool's purpose without extraneous information. Every part earns its place.

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 adequate for a simple audit check with only two parameters. However, it lacks details about what 'Standards 4, 9' refer to and does not explain the return format or behavior when issues are found. Could be more complete.

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 has 100% description coverage for both parameters (projectRoot, allowlists). The description adds context ('privacy policy', 'external-service SDKs') but does not enhance understanding beyond the schema. Baseline 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 it is a 'Warn-only check that the privacy policy names every external-service SDK the app depends on', providing a specific verb (check) and resource (privacy policy vs SDKs). It also references 'Standards 4, 9' which differentiates it from other audit tools like 'aadc.audit_sdks' or 'aadc.audit_defaults'.

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 usage contexts (privacy policy checks) but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'aadc.audit_sdks') or when not to use it. No exclusions or prerequisites are mentioned.

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 full burden. It states 'audit' (likely non-destructive) but does not disclose whether the tool modifies files, generates reports, or requires specific permissions. Behavioral details like output format or side effects are missing.

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 sentence, highly concise. It front-loads the key action and scope, though it could benefit from a brief note on output or return value to improve structure without adding length.

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 no output schema, the description should clarify what the tool returns or produces, but it does not. The reference to standards is modestly helpful given sibling tools for reading standards. Overall, the description is adequate but leaves gaps about outputs and deeper 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 coverage is 100%, so the description does not need to add parameter details. The description does not provide extra meaning beyond the schema, meeting the baseline of 3.

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 identifies the tool's purpose: auditing user-facing copy for reading grade above an age-appropriate threshold, referencing specific standards (4, 11). This distinguishes it from sibling audit tools, though the exact meaning of the standards is not elaborated.

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 usage for reading grade audits by naming the action and standards, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. Given the sibling tools list, the agent can infer specialization, but explicit guidance is absent.

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 full burden. It states the tool audits for specific SDKs and outside allowlist, but does not disclose whether it modifies files, what happens on success/failure, or other behaviors like output format or error handling. For a tool with no annotations, this is insufficient transparency.

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 sentence that efficiently communicates the main action, target files, and what it audits for. It is front-loaded with the verb and resource, and every part is informative with no 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?

Given the tool has 2 parameters (one nested object) and no output schema, the description adequately covers the purpose and what it checks, but lacks details on output format, how the allowlist parameter works, and how it integrates with sibling tools. It is sufficient but not comprehensive.

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%, so baseline is 3. The description does not add meaning beyond the parameter names and schema descriptions. It does not explain how allowlists work or provide examples, so it adds no extra value over the schema.

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 verb 'Audit' and the specific resource 'dependency manifests (pubspec.yaml, package.json, requirements.txt)'. It further specifies what it audits for: analytics/advertising/tracking SDKs or any dependency outside the allowlist, distinguishing it from sibling audit tools by its focus on SDKs and allowlists.

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 usage for auditing SDK dependencies against allowlists, referencing Standards 5,9,12,13, but it does not explicitly state when to use this tool versus alternatives like aadc.audit_all or aadc.audit_defaults. There is no guidance on when not to use it or what prerequisites are needed.

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 does not state whether the tool is read-only, requires specific permissions, or has side effects. The term 'Audit' implies read-only, but this is not explicitly confirmed.

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, front-loaded sentence that conveys the essential purpose without extraneous detail. Every word contributes to meaning, making it highly concise and efficient.

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 simplicity (2 optional params, no output schema, no annotations), the description covers the core purpose but lacks details on return format, behavior, or how to interpret results. It is adequate but not comprehensive.

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 has 100% coverage, describing both parameters adequately. The description adds marginal value by referencing 'Standards 7, 9' but does not elaborate on parameter usage or provide semantic meaning beyond the schema.

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 audits 'Sentry error-reporting initialisation for child-data hygiene' with specific concerns (PII scrubbing, no session replay) and references 'Standards 7, 9'. This distinguishes it from sibling audit tools that target different resources or standards.

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 no guidance on when to use this tool over sibling audit tools (e.g., audit_all, audit_sdks) or any prerequisites. It only states what the tool does without contextual usage instructions.

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 does not disclose whether the tool modifies files, requires permissions, or handles non-compliance. The audit nature implies read-only behavior, but this is not explicitly stated, leaving ambiguity.

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, concise sentence that quickly conveys the tool's purpose. It is front-loaded and contains no redundant information, earning its place.

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 tool with no output schema and standard parameters, the description sufficiently covers the audit purpose. However, it could be more complete by indicating what the tool returns (e.g., a report of violations or success) or how failures are handled. Slight gap given absence of output schema.

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% for both parameters, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides (projectRoot and allowlists are self-explanatory).

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 verifies that every audio/video player declares an explicit volume cap, referencing specific standards (1 and 14). It uses a specific verb ('verify') and resource ('audio/video player volume cap'), distinguishing it from sibling audit tools like audit_network_isolation or audit_hardcoded_url.

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 no guidance on when to use this tool versus alternatives, such as other audit tools. It does not specify prerequisites, exclusions, or situational context, leaving the agent without decision-making support.

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 full burden. It discloses the tool returns 15 standards with one-line summaries, implying it is a read-only operation. It does not mention format or performance, but for a simple list tool, it is sufficiently transparent.

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 concise sentences with zero wasted words. The main action ('Return the 15 AADC standards') is front-loaded, and usage guidance is provided succinctly.

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 simple listing tool with no parameters and no output schema, the description provides all necessary information: what is returned (15 standards with one-line summaries) and when to use it (filling conformance statements). No gaps.

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?

There are zero parameters, so schema coverage is 100%. The description adds no parameter information because none is needed, meeting the baseline expectation for a parameterless tool.

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 it returns 'the 15 AADC standards with their one-line statutory summaries', using a specific verb ('Return') and resource ('AADC standards'). It distinguishes from sibling tools like aadc.read_standard, which likely returns a single standard, and audit tools that perform different actions.

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 advises using this tool 'as a reference when filling in a conformance statement', providing clear usage context. It does not explicitly state when not to use it or name alternatives, but the sibling context implicitly covers that.

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 burden. It implies a read-only operation by stating 'return the full text,' but does not explicitly declare it as non-destructive or disclose any side effects. Adequate but minimal.

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 short sentences, front-loaded with the action and resource. Every word adds value; no fluff. Ideal conciseness for a simple 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 simplicity (one parameter, no output schema), the description is complete enough: it explains purpose, parameter range, and usage. Could note return format (text string), but not essential.

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 0%, so the description adds crucial meaning: 'by number (1-15)' matches schema constraints and clarifies the parameter's role. It explains what the number represents (the standard number), going beyond the bare schema.

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 action (return full text) and resource (AADC standard by number 1-15). It distinguishes from sibling tools implicitly by specifying retrieval of full text, while a sibling lists standards.

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 usage context is provided: 'Use this when you need the verbatim wording for a conformance statement or DPIA.' This gives clear guidance, though it does not mention when not to use it or alternative tools.

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