Citation Safe Verifier

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

Annotations provide no safety hints (readOnlyHint=false, destructiveHint=false). Description adds billing info (each item billed individually, batching doesn't bypass limit), authentication requirement, and that anonymous calls are not supported. No contradictions.

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 well-structured: front-loads the core purpose, then covers billing, limits, and auth in separate sentences. No unnecessary words; 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?

With a simple input schema (1 parameter, no output schema) and minimal annotations, the description provides all necessary context: purpose, usage guidelines, behavioral traits (billing, auth), and constraints. 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?

Schema coverage is 100%, so the schema already describes the texts parameter. Description adds practical details: each item processed separately, max 10 items, 64k chars per item. This adds 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 it runs the same 3-layer citation verification as verify_citation across multiple texts in a single call, with a specific verb and resource. It distinguishes from siblings like verify_citation by focusing on batching.

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 states when to use (multiple texts in one call) and when not (anonymous batch not supported, use verify_citation for anonymous single-text checks). Provides limits (max 10 items, 64k chars per item) and auth requirement.

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 declare readOnlyHint=true; description adds that it returns full per-citation results and the source of the ID. No contradictions.

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, well-structured sentence that is front-loaded and contains 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 single parameter and no output schema, it adequately describes what the tool does and returns. Could mention output size or pagination but not necessary for this simple 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 covers 100% with UUID format; description adds semantic meaning: the ID comes from specific actions or share links, going 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?

Description clearly states it retrieves a past verification by ID and returns full per-citation results. It distinguishes from sibling tools like verify_citation/verify_document which run new verifications.

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?

Provides specific sources for the ID (from verification actions or share link), implying when to use. Lacks explicit when-not-to-use or alternatives, but context is sufficient.

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?

Description adds deterministic, Layer 1, no LLM, and database source info beyond annotations which only say readOnlyHint. Also discloses rate limits and authentication requirements.

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?

Concise and well-structured: purpose first, then differentiation, then usage limits, then authentication. No wasted 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 tool's simplicity (one parameter, no output schema), the description covers all needed aspects: what it does, when to use, rate limits, and authentication. 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?

Schema already describes the citation parameter with 100% coverage. Description adds concrete examples like '410 U.S. 113' and 'Roe v. Wade, 410 U.S. 113 (1973)', providing useful formatting guidance.

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 the tool checks if a single legal citation is real, using a deterministic no-LLM method against CourtListener. It distinguishes from siblings like verify_brief which handles multiple citations.

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 says when to use this tool (single citation) vs when to use verify_brief (multi-citation brief). Also covers free tier limits and how to get unlimited access with an API key.

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 declare readOnlyHint=true and destructiveHint=false. The description adds value by clarifying the empty array return behavior and that data is public, going beyond 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 concise sentences, front-loaded with purpose, 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?

With full schema coverage, clear annotations, and description handling edge cases (empty array), the tool is completely specified for its simple purpose. No output schema needed as return behavior is described.

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%, with the parameter description covering free-text matching. The description reiterates this but doesn't add significant new syntactic details 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 it searches a phantom-citation registry by case name or AI system. It distinguishes itself from siblings like verify_citation which handles real citations, and specifies the registry is for known hallucinated citations.

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 indicates it's read-only and public data, and explains that an empty array (not error) is returned for no matches. While it doesn't explicitly name alternatives, the sibling tool names provide context for when to use this tool vs others.

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 declare readOnlyHint=true and destructiveHint=false. The description adds that data is 'public' and emphasizes 'real court sanctions/orders', but does not contradict annotations. It provides some additional context about data source (same as website) but not rich behavioral details beyond what annotations cover.

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, front-loaded with purpose, no waste. The first sentence covers verb, resource, and search methods; the second adds nature (read-only, public) and source. 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?

For a simple search tool with 2 parameters and clear annotations, the description is adequate. It explains what is searched, how, and the public nature. Absence of output schema is acceptable for a search tool. However, it could briefly mention that results are returned as a list, but not necessary given simplicity.

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%; both parameters have descriptions. The tool description adds 'by court name, party/case name keyword, or free-text keyword' which partially aligns with schema but does not significantly enhance meaning beyond the schema's own descriptions.

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 'Searches', the resource 'CitationSafe's database of real court sanctions/orders', and search methods 'by court name, party/case name keyword, or free-text keyword'. It distinguishes from siblings by focusing specifically on sanctions related to AI-hallucinated citations, unlike sibling tools such as 'verify_brief' or 'is_this_case_real'.

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 (when searching for sanctions) but does not explicitly state when not to use or provide alternatives among sibling tools. It mentions 'Read-only, public data' as context but lacks direct comparisons to other tools like 'search_phantoms' or verification tools.

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 provide readOnlyHint. Description adds that checks are deterministic and no LLM used, that Layer 3 is excluded, and clarifies free tier caps. No contradictions.

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?

Three sentences: core function with layers, limitation and alternative, and free tier info. No wasted words, well-structured.

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 one parameter and no output schema, the description covers functionality, limitations, tier restrictions, and relation to siblings. Enough for an agent to select and invoke 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 has 100% coverage for single param 'text' with description. Description adds that text can be a brief excerpt or motion, reminds of max length, and explains that one call counts as one check regardless of citation count.

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 runs deterministic existence and quote-match checks on every citation in a brief/excerpt, returning one verdict per citation. Distinguishes itself from sibling 'is_this_case_real' as the multi-citation counterpart.

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 tells when to use (verifying citations in brief/excerpt), when not (for proposition support/Layer 3), and alternatives (verify_citation with sign-in). Also explains free tier limits and API key bypass.

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 value beyond annotations by revealing deterministic Layer 1 (no LLM), paid-tier dependency for Layer 3, and output format (never bare true/false). annotations are neutral and not contradicted.

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 front-loaded with the core action, uses four efficient sentences without repetition, and every sentence adds key information such as layers, output, and disclaimers.

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 fully explains return values (VERIFIED/UNCONFIRMED/etc.), mentions source links, and covers behavioral nuances like paid tiers. It is complete for a single-parameter 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 coverage is 100% (parameter 'text' has a description). The tool description contextualizes this parameter by explaining how the text is processed, adding meaning beyond the raw 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 verifies legal citations in text against primary sources using three layers, and specifies the output format per citation. It distinguishes itself from general citation tools by detailing the layered approach and output types.

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 use for verifying citations in text but does not explicitly when to prefer this tool over siblings like batch_verify_citations or verify_document, nor does it provide exclusion criteria.

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 that the tool fetches a document and runs verification, but does not clarify side effects or why readOnlyHint is false. This creates ambiguity between the description's read-only implication and the annotation indicating potential writes.

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 action and purpose, and contains no fluff. Every word 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?

For a simple tool with one parameter and no output schema, the description covers purpose, input format, and usage context. Lacks mention of return values or error handling, but these are partly covered by annotations.

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 'url' is fully described in the schema (100% coverage). The description does not add additional meaning beyond what the schema provides, so baseline 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 verb 'fetches' and 'runs verification' on a document URL, and differentiates from sibling tools like verify_citation by specifying input method (URL vs pasted text).

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 states when to use this tool: 'Use this when you have a link to a brief rather than pasted text.' This provides clear context, though it does not explicitly mention when not to use it.

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