bies-guardian

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

Goes well beyond annotations: describes determinism, sealed nature, rules engine (0-LLM), regulatory grounding (KR/US law), and return fields (verdict, severity, replay_hash). No contradiction with readOnlyHint=true or openWorldHint=false.

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?

Extremely concise: two sentences that front-load the core purpose and then add critical caveats. No fluff or 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?

Given no output schema, the description adequately summarizes return fields and explains the tool's limitations. It could optionally detail the verdict values or severity scale, but is sufficient for an agent to understand the tool's role.

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%, but the description adds value by clarifying that 'copy' expects exact public claim text, and that 'market' defaults based on 'lang'. This extra context improves semantic understanding beyond the schema alone.

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: a 'deterministic, sealed pre-publication verdict on a PUBLIC claim', with examples like marketing copy and ad headlines. It distinguishes itself from sibling tools (idea_rehearsal, rejudge_claims) by focusing on pre-publication verdicts and legal compliance.

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?

Explicitly instructs to 'Call this before a public claim ships' and specifies what it is NOT (legal advice, market proof). While it doesn't explicitly contrast with siblings, the context implies it's for final pre-publication checks rather than rehearsal or rejudging.

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 adds significant behavioral context beyond the annotations (readOnlyHint, openWorldHint). It states the tool is deterministic, retrieval-grounded, and reproducible, which are not captured by annotations. It also clarifies what the tool is not (market proof, investment advice), aiding accurate agent reasoning.

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 (about 60 words) and front-loaded: the first sentence clearly states the core purpose. Every sentence adds value, including warnings and usage guidance. There is no 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 provides enough context for a straightforward tool with 3 parameters and no output schema: it lists the verdict options, explains reproducibility, and states the use case. It lacks explicit details on the seal format or how the verdict is derived, but overall it is complete enough for an agent to select and invoke the tool 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 description coverage is 100%, so a baseline of 3 is appropriate. The description does not add new information about parameters beyond what the schema already provides; it only gives overall context about the idea parameter ('your own words'). The parameter descriptions in the schema are adequate but the tool description does not enhance them.

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 that the tool returns a verdict (Proceed/Conditional GO/Hold·Redesign) with a reproducible seal based on a founder's business idea. It distinguishes itself from sibling tools by emphasizing it is for business ideas, not public claims, which are likely handled by claim_safety_verdict and rejudge_claims.

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 the tool to 'pressure-test an idea before committing' and warns that it is not market proof or investment advice. It implies the appropriate context (early-stage idea testing) but does not explicitly state when not to use it or compare to sibling tools, though the contrast with 'public claim' provides indirect guidance.

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?

Beyond the annotations (readOnlyHint=true, openWorldHint=false), the description adds critical behavioral details: 'Deterministic, sealed, stateless (nothing stored)', 'conservative by design' (top-level verdict never changes), and explains what moves (4 axes). This goes well beyond what annotations 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 two sentences long, with the first sentence stating the purpose and the second providing constraints and behavior. No wasted words; information is front-loaded 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 tool with nested objects and no output schema, the description covers input semantics, behavioral constraints, and deterministic nature. It could mention the return format (axes updates), but the explanation of what moves (4 axes) partially compensates. Overall, fairly 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?

With 100% schema description coverage, the description adds meaning by explaining the origin of 'artifact' (returned by claim_safety_verdict) and the nature of 'observations' (evidence events). It does not repeat the schema but provides context that aids 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 the tool's purpose: 'Re-judge a prior claim-safety verdict against new EVIDENCE.' It specifies the verb (re-judge) and the resource (claim-safety verdict), and distinguishes it from siblings by referencing the prior verdict and new evidence.

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 context on when to use the tool (with new evidence) and what behavior to expect (e.g., top-level verdict never changes). However, it does not explicitly state when not to use it or name alternative tools for comparison.

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