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

No annotations are present, so the description carries the full burden of behavioral transparency. It warns against supplying prompt bodies, which is useful, but it does not clarify whether the tool is read-only, whether it has side effects, or what data it accesses beyond the events input.

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 concise and front-loaded, giving the primary action and target in the first sentence. The second sentence adds an important security boundary without unnecessary detail 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?

With no output schema, no annotations, and an underspecified events parameter, the description does not fully convey what the tool returns or how the analysis results are presented. It covers the high-level purpose but leaves critical operational details missing.

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 sole parameter 'events' is an array of objects with no schema or field descriptions. The description indicates that the input is telemetry and focuses on signal types, but it does not explain the expected structure, required fields, or constraints of each event object, leaving significant ambiguity.

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: analyzing customer-controlled model API telemetry for specific abuse signals. It names concrete signal types (burst, cost-drain, repeated-query, auth-failure) and adds a security constraint, but does not explicitly contrast with the sibling security tools.

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?

There is no guidance on when to use this tool versus the sibling tools. The description implies it is for telemetry analysis, but it does not specify conditions or alternatives, leaving the agent to infer appropriate usage.

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 of behavioral disclosure. It only states the action ('evaluate') without specifying return values, side effects, whether it is read-only, or any constraints (e.g., 'local' policy source). The description adds minimal context beyond the basic 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 with no filler. However, it is under-specified for the tool's complexity—three parameters with nested objects and no output schema. The brevity is efficient but does not structure information (e.g., separate usage, output, or examples) to aid comprehension.

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 three required parameters, nested objects, no output schema, and no annotations, the description is severely incomplete. It does not explain what the tool returns, how the policy should be structured, or what 'local' means. An agent cannot reliably call this tool without additional information.

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%, and the description does not explain any of the three required parameters (tool_name, arguments, policy). Since the schema provides no descriptions and the description does not compensate, the agent has no understanding of how to construct valid arguments or what the policy object should contain.

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 function: evaluating an MCP tool call against a policy. It uses a specific verb ('Evaluate') and names the resource ('an MCP tool call'). However, it does not explicitly differentiate from sibling tools like check_tool_call_safety, though the mention of 'allowlist/approval/destination policy' hints at a distinct policy-checking role.

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 is provided on when to use this tool versus its siblings (e.g., check_tool_call_safety, scan_prompt_for_injection). There is no mention of prerequisites, exclusions, or alternative selection criteria, leaving the agent to infer usage context.

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 providing safety hints, the description must carry full weight. It indicates the tool classifies 'before execution', implying it does not execute the call itself, but it omits details about side effects, permissions, or how the result is used.

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 immediately conveys the core action and purpose. There is no extraneous information or redundant phrasing.

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 and no description of return values, errors, or example usage, the tool is incomplete from an agent's perspective. The description does not explain what the classification result looks like or how to interpret 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?

The schema provides no descriptions for the two parameters, and the description adds no detail about what tool_name or tool_input should contain. Given the schema coverage is 0%, the description fails to compensate, leaving parameter semantics entirely unspecified.

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 'classify' and the resource 'proposed tool call', with a specific outcome (allow/ask/deny). It is distinct from sibling tools that focus on scanning, analysis, or policy checking.

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 explicit guidance on when to use this tool versus the sibling tools. The mention of 'before execution' implies a pre-check scenario, but it does not contrast with alternatives or specify conditions for selection.

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, and the description does not mention whether the tool performs read-only operations, has side effects, or returns a specific output. Since the tool is described as 'mapping' a report to frameworks, it is likely non-destructive, but this is not explicitly stated. The description carries the full burden for behavioral transparency and falls short.

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 concise and to the point, with no redundant information. It clearly states the action, the target frameworks, and a critical caveat in a single sentence. The structure is efficient and easy to parse.

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 lacks important contextual details for an agent to use the tool correctly: it does not specify the output format (e.g., a report object, a list of mappings, a JSON structure), whether the input report must conform to a particular schema, or any examples. Given the absence of an output schema, the description should compensate by explaining the expected return value, but it does not.

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 only parameter 'report' is described as 'A report object containing a findings list,' which gives a basic idea but lacks detail about the required structure, such as field names or types. Since there is only one parameter and no enums or additional metadata, the description adds some value but does not fully clarify the expected input shape.

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: mapping an LLMSecurity scan report to OWASP LLM 2025, NIST AI RMF, and MITRE ATLAS coverage evidence. It also distinguishes itself from the sibling scanning tools by focusing on mapping rather than scanning. A higher score would require specifying what 'coverage evidence' looks like.

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 (when you have an LLMSecurity report to map) and gives a negative constraint ('This is not a compliance certification'), but it does not provide explicit conditions, such as when to prefer this over other tools or what input format is expected. More concrete usage guidance would improve this dimension.

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 must carry the behavioral disclosure burden. It does convey that the scan is local and limited to listed file types, but it does not state whether the operation is read-only, what it does on detecting injection, or how it treats directories versus files. This is adequate but not thorough.

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 entire description is a single front-loaded sentence with no filler. It packs the action, target file types, scope, and purpose into one concise statement.

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 one-parameter tool, the description plus schema covers what to scan and where, but with no output schema the description does not explain what the agent should expect as a result or how findings are reported. Sibling differentiation is also left to inference, leaving minor 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?

Schema description coverage is 100%, so the path parameter is already fully documented ('config file or repository root; defaults to the current directory'). The tool description adds no parameter-specific meaning, matching the baseline of 3 for high coverage.

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 ('Scan'), enumerates the exact resources (AGENTS.md, CLAUDE.md, SKILL.md, .claude, .codex), and states the goal (prompt injection) plus local scope. This clearly differentiates it from sibling tools like scan_prompt_for_injection, which targets arbitrary prompts rather than config files.

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 for scanning local agent/config files for injection, but it does not explicitly state when to prefer it over siblings such as scan_prompt_for_injection, scan_skill_trust, or scan_rag_source. No exclusions or alternative conditions are given.

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 for behavioral disclosure. It mentions applying patterns but does not state whether the operation is read-only, what happens on a match, return format, or any side effects. For a security scanning tool, this is a notable gap.

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 with no redundancy. It is appropriately concise, though brevity comes at the cost of essential details.

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 one-parameter tool, the description lacks essential context: no mention of output, expected behavior on detection, or how to interpret results. With no annotations or output schema, the description is insufficient for an agent to call it confidently.

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 schema provides only a string parameter with zero description coverage. The description refers to 'supplied instructions', giving some context that the text is the content to scan, but does not explain limits, encoding, or interpretation. Minimal added value 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 a specific action ('Run') on a specific resource ('existing PromptGuard patterns') against a target ('supplied instructions'). It indicates a scanning operation for injection. It is not a tautology and is distinguishable from sibling tools, though it doesn't explicitly name alternatives.

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 is given on when to use this tool versus sibling scanning tools like scan_rag_source or check_tool_call_safety. The description implies it is for checking prompts for injection, but does not specify conditions, prerequisites, or exclusions.

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 implies a non-destructive scanning operation but does not explicitly state that documents are not modified, nor does it disclose side effects, output behavior, or failure modes. With no annotations present, the description carries the full transparency burden and only partially meets it.

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, focused sentence that conveys the tool's purpose, target, and timing without unnecessary detail. It is concise and easy to parse.

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 one-parameter tool with no output schema, the description gives enough to invoke it correctly. However, it does not describe what the scan returns or how results are reported (e.g., findings list, exit code), which would be helpful for agents interpreting the outcome.

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 path parameter is described as accepting a supported source document or directory and having a default of the current directory. This adds useful context beyond the raw schema, though the term 'supported' is vague and could leave file-type or format ambiguity.

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 local RAG source documents specifically for prompt injection, secrets, and PII before indexing. This differentiates it from sibling tools like scan_prompt_for_injection, which targets prompts, and check_mcp_policy, which targets policies.

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 phrase 'before indexing' gives a concrete usage condition, indicating when this scan should be performed. However, it does not explicitly contrast with sibling tools or explain when to choose this over scan_prompt_for_injection or scan_skill_trust, so some inference is still required.

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 of behavioral disclosure. It only says 'Build' which implies creating an inventory, but does not state whether it is read-only, whether it modifies files, what permissions are required, or what side effects might occur. This is a significant gap for a security-related tool.

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 with no redundant wording. It front-loads the main action and object, which is efficient. However, its brevity comes at the cost of missing essential details, so it is not well-structured for completeness.

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 security focus and the absence of annotations, output schema, and parameter descriptions, the description is severely incomplete. It does not explain what a 'local trust inventory' entails, what inputs are expected, what outputs are produced, or any context for safe usage. This is inadequate for a tool with even a single parameter.

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 sole parameter 'path' has no schema description and the description text does not mention it at all. With 0% schema coverage, the description fails to clarify the expected format, meaning, or role of the parameter, making it impossible for an agent to correctly supply it without additional knowledge.

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 action ('Build') and resource ('local trust inventory') for skills, MCP package manifests, and risky install scripts. It is distinct from sibling tools like scan_agent_config or check_tool_call_safety, though it does not explicitly name any sibling to differentiate itself from.

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 no indication of when to use this tool versus the alternatives. There is no mention of scenarios, prerequisites, or exclusions. An agent must infer the purpose from the verb and object alone, leaving ambiguity about when to choose this over scan_agent_config or map_security_coverage.

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