bies-guardian

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

Annotations declare readOnlyHint=true and openWorldHint=false, but the description adds substantial behavioral context beyond these: it is deterministic (0-LLM), sealed, grounded in specific regulations (KR 표시광고법 / US FTC), and returns a reproducible replay_hash. It also clearly frames the tool's role as a pre-publication check, not a legal or marketing approval. No contradictions with annotations.

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, front-loaded with the core purpose ('Deterministic, sealed pre-publication verdict'), then succinctly covers output, legal grounding, and usage timing. Every sentence adds value with no fluff or repetition.

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?

Despite no output schema, the description explicitly reports return values (verdict, severity, replay_hash), which is essential for a tool with no structured output definition. It also explains the regulatory basis and the exact timing of use. Given the tool's moderate complexity (3 params, no nested objects), the description covers all necessary operational 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 description coverage is 100%, so the schema already documents 'copy', 'lang', and 'market' with meaningful descriptions. The description adds context that 'copy' is a PUBLIC claim and offers examples (marketing copy, product page, ad headline), but it does not meaningfully enhance understanding of 'lang' or 'market' beyond what the schema provides. 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 opens with a specific, action-oriented phrase: 'Deterministic, sealed pre-publication verdict on a PUBLIC claim', immediately clarifying the tool's resource (public claims) and output (verdict). It further distinguishes itself by listing concrete claim types ('marketing copy, product page, ad headline') and contrasting with legal advice/approval. This strongly delineates it from sibling tools like idea_rehearsal 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 states when to use the tool ('Call this before a public claim ships') and provides exclusions ('NOT legal advice, NOT market proof or launch approval'). However, it does not name alternative tools or explicitly describe when not to use it beyond these exclusions, so it falls short of full alternative 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?

Annotations already indicate readOnlyHint=true, and the description adds behavioral context: deterministic, retrieval-grounded, reproducible, and explicitly not market proof or investment advice. This goes beyond the annotation by explaining the nature of the output and its 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 somewhat lengthy but well-structured, front-loading the core function and then providing verdict types, reproducibility, disclaimers, and usage. Every sentence serves a purpose, though the verdict list is detailed.

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 compensates by listing possible verdict outcomes and clarifying what the tool does and does not do. Combined with readOnlyHint and parameter schema, it provides a sufficiently complete picture for a decision-support 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 description coverage is 100%, so baseline is 3. The description does not add parameter-specific details beyond the schema, but none are needed since the schema already describes each 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 description clearly states the tool produces a deterministic decision-rehearsal verdict on a business idea and enumerates the possible verdict categories. It explicitly distinguishes from 'a public claim', aligning with sibling claim-focused tools, making its purpose 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?

The description says 'Use to pressure-test an idea before committing', providing a clear context for use. It also notes 'not a public claim', implicitly excluding claim-related uses and separating from siblings. It lacks explicit alternative tool names but the context is clear.

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 goes well beyond the readOnlyHint annotation by disclosing that the top-level verdict is conservative and never changes, what the four movable axes are, and that the tool is deterministic, sealed, and stateless. This gives the agent critical behavior information that annotations alone do not 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 four sentences, each earning its place: purpose, input requirements, behavioral constraints, and processing guarantees. It is front-loaded with the core action and avoids any 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?

Given the tool's complexity (nested observations, no output schema), the description covers purpose, inputs, behavioral nuances, and guarantees. It mentions the four axes that move, giving a sense of the output, but it does not explicitly describe the return format or error conditions, which would make it fully 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 coverage is 100%, so the description doesn't need to explain parameters. It does add a simple 'what happened' gloss for observations and confirms the artifact comes from claim_safety_verdict, but these are minor clarifications. The schema already defines the nested structure and enums, so the description doesn't meaningfully expand parameter semantics.

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 uses a specific verb ('re-judge') and resource ('claim-safety verdict'), and distinguishes itself from sibling tools by requiring the artifact from claim_safety_verdict and focusing on evidence-driven re-evaluation.

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 usage context: it tells the user to pass the artifact from claim_safety_verdict and observations, and explains that the top-level verdict never changes. While it doesn't explicitly state 'when not to use' or name alternatives, the dependency on a prior verdict implies use after an initial claim_safety_verdict, which is sufficient guidance.

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