ai-guardrails

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

Without annotations, the description carries full responsibility but only states it is a heuristic, omitting important behavioral traits like whether it requires authentication, has side effects, or handles errors.

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 with two sentences focused on purpose and output, with no redundant 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?

While it covers the basic function and output, it lacks behavioral details like whether the tool is deterministic or probabilistic, and does not define risk levels, making it 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?

Schema description coverage is 0%, so the description partially compensates by stating the text is an LLM output for hedge phrase scoring, but lacks details on length limits, format, or examples.

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 as heuristic scoring of LLM hedge phrases correlated with hallucinations, distinguishing it from sibling tools like check_safety and detect_pii through a specific verb and resource.

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 alternatives, such as check_safety or full_check, leaving the agent to infer usage from sibling names alone.

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?

Without annotations, the description only mentions output and method. It does not disclose whether the tool has side effects, requires authentication, or any limitations like rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff. Every word adds value. Front-loaded with purpose and output summary.

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 (1 param, no output schema, no annotations), the description covers basic function and output but lacks usage guidelines and behavioral details. Adequate but with clear 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?

The single parameter 'text' is not described in schema (0% coverage). The description implies it is the content to check but adds no further semantics (e.g., length, format). Adequate for a simple parameter but not compensating for schema gaps.

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?

Clearly states the action ('check text'), the resource ('text'), the method ('weighted keyword detection'), and the output ('0-1 score and verdict'). Distinguishes from sibling tools like check_hallucination or detect_pii.

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 explicit guidance on when to use this tool vs siblings. Does not describe contexts where it is preferred or alternatives for other types of content checks.

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 exist, so the description carries full burden. It mentions what is detected but omits behavioral details like whether the tool is read-only, returns locations, or confidence scores.

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, clear sentence with no wasted words. It could be slightly improved by front-loading the most critical 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 no output schema, the description should explain what the tool returns (e.g., list of matches, boolean). It does not, leaving a gap for the 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 coverage is 100%, so the schema already describes the 'text' parameter. The description adds no additional meaning beyond the schema, earning a baseline 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 states the tool detects PII in a text string and lists examples. However, it does not differentiate from sibling tools like redact_pii or check_safety.

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 the sibling tools listed.

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 disclose all behavioral traits. It states the tool runs checks but does not mention whether it is read-only, what permissions are needed, or what the output format is. The description is insufficient for full 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 only two sentences, front-loaded with the purpose, and contains no unnecessary words. Every sentence earns its place by specifying behavior and customization.

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 and no annotations, the description is somewhat complete for a simple tool, explaining what it does and how to customize. However, it lacks details on return format, error cases, or prerequisites, which are still 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 input schema has 0% description coverage, so the description adds significant value by explaining the default for 'checks' and how to run all checks. However, it does not clarify the 'text' parameter beyond being a string, which could be improved.

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 multiple checks (pii, safety, hallucination) in one call, distinguishing it from sibling tools that run individual checks. The verb 'run' and resource 'checks' are specific and appropriate.

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 explains the default behavior and how to specify all checks, but it does not explicitly advise when to use this combined tool vs. the individual siblings (e.g., use for multiple checks; use individual for a single check). No when-not 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?

Describes mode behaviors (mask replaces with [REDACTED], tag uses typed placeholders) but lacks details on return format, idempotency, or error handling. With no annotations, this leaves some behavioral 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?

Two sentences, each serving a distinct purpose. Front-loaded with action and scope, then mode details. 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?

Covers purpose and modes adequately for a simple tool. Lacks output specification (e.g., returns redacted string) and edge cases, but close to complete given low complexity.

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?

Adds meaning for 'mode' parameter beyond enum values (explains output for each), but provides no additional info for 'text' parameter. Schema coverage is 0%, so partial compensation.

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?

Clearly states the tool redacts PII from text. Specifies two modes (mask and tag) with distinct behaviors, distinguishing it from siblings like detect_pii which only detect.

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?

Implies usage for redacting PII but does not explicitly contrast with siblings (e.g., when to use detect_pii instead). No when-not-to-use or alternative recommendations.

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