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 explains output fields, instructs agents to branch on structured fields rather than prose, describes high_risk_only filtering behavior, and warns that batch repairs must be proposed to the user rather than silently applied. It does not cover auth, rate limits, or error behavior, but the key operational behaviors are disclosed.

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 dense and information-rich, with the core purpose front-loaded. Most sentences add meaningful guidance, but there are a few awkward phrases such as 'Set review_summary.suggested_fix_summary.auto_apply_allowed=false means...' which could be cleaner. Overall, it earns its length given the tool's complexity.

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, the lack of output schema, and the absence of annotations, the description covers a lot: input shape, key output fields, actionable guidance for agents, and high_risk_only behavior. The main gap is max_workers semantics and a bit more detail on what risk_ranking and per-citation report contain, but the description is largely sufficient for correct invocation.

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 must compensate. It thoroughly documents the citations parameter's object shape and the high_risk_only parameter's effect, but it does not explain max_workers at all beyond the schema's name and default. This partial coverage leaves one parameter semantically underspecified.

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 clear, specific statement: 'Verify MANY citations at once.' This gives a verb, resource, and scope, and the emphasis on 'many' differentiates it from sibling tools like verify_citation_tool, which appears to handle single citations. It also describes the returned report structure, reinforcing the tool's batch purpose.

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 clearly indicates the tool is for verifying many citations at once, which establishes a primary use case. It does not explicitly name alternatives or say when not to use this tool, but the batch-focused language and sibling list provide enough context for an agent to infer the appropriate 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?

With no annotations, the description carries the full behavioral burden, and it delivers: it names the return components, instructs agents to branch on triage_plan and suggested_fix, warns against silently editing citations, explains auto_apply_allowed=false, describes evidence_scope=full_text behavior, and clarifies high_risk_only preservation. This is strong, actionable 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 front-loaded and dense with useful operational details, and every sentence contributes information. It loses a point because the paragraphs are long and the structure could be improved with bullets or shorter scannable sentences.

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 complex tool with no output schema and no annotations, the description covers invocation, input shape, output routing, and filtering behavior well. Gaps remain around counterevidence-related parameters and explicit sibling selection, but the core guidance is sufficient for correct basic use.

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 description gives detailed semantics for `items` and `high_risk_only`, which is valuable given 0% schema coverage. However, three parameters (`max_workers`, `counterevidence_top_k`, `include_counterevidence`) are not explained, and the top-level `lang` parameter is not clearly distinguished from the per-item `lang`. Compensation is partial.

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 verb and resource: 'Judge MANY claim-citation support pairs at once.' It clearly conveys batch action on claim-citation pairs, but it does not explicitly differentiate the tool from siblings such as check_claim_support_set_tool or verify_citation_tool, so it stops short of full sibling differentiation.

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 'at once' phrasing implies this tool is for batch assessment, and the description gives substantial guidance on constructing items and handling output. However, it never explicitly says when to choose this tool over alternatives or provides exclusions, leaving some selection reasoning to inference.

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, and it delivers: it explains caller-provided full-text handling, the evidence_scope tagging, that gated full text will not be fetched, the aggregation behavior, the support_mode_details policy, the minimum support requirement, and how contradictions are surfaced.

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 a crisp summary and then efficiently adds behavioral details. It is somewhat dense and jargon-heavy, but each sentence contributes meaningful information and there is no 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 core behavior is well covered, including input semantics, aggregation policy, support threshold, and risk signaling. However, with no output schema and no annotations, the description leaves counterevidence parameters and the full return shape underspecified, making it adequate but not 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 description coverage is 0%, so the description must compensate. It thoroughly explains the citations parameter, including accepted object shapes and full-text evidence rules, and claim is self-evident. However, lang, counterevidence_top_k, and include_counterevidence are not explained at all, leaving majority of parameters underspecified.

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 verb and resource: 'Judge whether a SET of cited papers supports one claim sentence.' The emphasis on SET and aggregated per-citation checks clearly distinguishes it from the singular sibling check_claim_support_tool.

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 makes the context clear: it is for judging a set of citations together and aggregating their support. It references verify_citation_tool for citation object format, which helps routing, but it never explicitly states when not to use this tool or names alternatives such as check_claim_support_tool.

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 behavioral burden and does so thoroughly. It discloses the paper-resolution step, the reranker+NLI ensemble, the precise meaning of insufficient_evidence, the no-gated-full-text-fetching policy, first-use model downloads, heuristic fallback, and multilingual configuration.

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 dense but every sentence adds operational value: purpose first, then verdict semantics, evidence scope, failure modes, and multilingual tuning. There is no filler 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?

For a complex tool with no annotations and no output schema, the description covers verdict semantics, fallback behavior, evidence scope, and model configuration. It stops short of describing the full return payload and the exact rules for identifying the paper, so some call details still rely on parameter-name inference.

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 only explicitly explains full_text, full_text_file, and two environment variables. The remaining parameters such as doi, arxiv_id, abstract, raw_text, evidence_text, evidence_chunks, lang, year, venue, and authors are left to be inferred from their names, with no guidance on how paper resolution uses 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 opening sentence states a specific action (judge whether a cited paper supports a claim) on a clear object, and it lists the exact verdicts. It does not explicitly differentiate from siblings such as verify_citation_tool or audit_claim_support_tool, but the tool's function is unmistakable.

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 useful input guidance: agents may pass full_text or full_text_file, and multilingual models can be enabled via environment variables. However, it never states when to choose this tool over alternatives like check_claim_support_set_tool or search_counterevidence_tool, so cross-tool routing is left implicit.

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 and handles it well. It discloses the default behavior ('does not contact OpenAlex/Crossref/arXiv/Semantic Scholar and does not load model weights') and the opt-in live probe (`check_sources=true`). This is more transparent than most tool descriptions.

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 with no waste: purpose, when-to-use, and behavioral defaults are each front-loaded in their own sentence. The structure is easy to scan and 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?

The description covers what the tool returns, when to call it, and the default/opt-in behavior for source checks. It doesn't describe the output structure, but given there is no output schema and this is a status tool, the provided information is sufficient for an agent to invoke and interpret the result at a high level.

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 must compensate, and it does. It explains that `check_sources=true` triggers a lightweight live probe and that `health_query` is used for that probe, adding meaning beyond the schema's type/default fields. It doesn't detail accepted query formats, but the default value provides a usable example.

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 verb+resource: 'Return MCP configuration and dependency status.' It clearly positions the tool as an entry-point diagnostic for setting up CiteGuard or troubleshooting, which distinguishes it from the citation-verification and claim-support sibling 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?

The description explicitly says 'Call this first when setting up CiteGuard or diagnosing surprising results,' giving clear context for when to use this tool. It doesn't explicitly name alternatives or state when not to use it, but the 'first' ordering implies it precedes the sibling 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?

With no annotations provided, the description carries the full burden and does well by disclosing behavioral limitations: the tool returns candidates only, does not prove contradiction, and does not alter support verdicts. It stops short of describing return structure or read-only guarantees, but the search-oriented language and limitation statements provide strong 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 concise and front-loaded: the first sentence states the tool's purpose, and the second clarifies scope and next steps. Every sentence adds value with no repetition 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?

For a two-parameter search tool with no output schema, the description gives enough high-level context to invoke it correctly and know what to do with results. It could be slightly more complete by describing the shape of a 'review candidate,' but the workflow guidance and clarity of purpose make it largely sufficient.

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 must compensate for the two parameters, but it does not explain claim or top_k. The parameter names and titles are somewhat self-explanatory, so this is not a 1, but the description adds no explicit parameter-level meaning and top_k is entirely unaddressed.

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 verb and resource: 'Search for scholarly records that may contain counter-evidence.' It further distinguishes the tool from siblings by explicitly stating it returns review candidates only and does not prove contradiction or change a support verdict, so an agent can tell it apart from verification or audit 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?

The description clearly states when not to rely on this tool: it does not prove contradiction and does not change a support verdict. It also gives the correct follow-up action, 'run claim-support checks on any promising candidate before editing text or replacing citations,' which aligns with the sibling tools while not requiring the agent to infer the workflow.

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 and does so well: it discloses live sources, the exact verdict vocabulary, the returned components (canonical record, diffs, suggested corrected citation, sources checked), and explains that not_found means unable to verify rather than proof of fabrication. This prevents misinterpreting a negative result.

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 compact and front-loaded: purpose first, then input modes, then return value, then caveats. Every sentence adds functional value and there is no repetition of schema properties 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?

Even without an output schema, it covers the main return values and the critical not_found caveat, and it is explicit about scope (existence/metadata verification, not claim support). It does not detail the exact shape of per-field diffs or the ambiguous verdict, but the tool can be invoked correctly from this definition.

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 0%, so the description must compensate. It adds the key distinction between raw_text and structured fields and names all seven parameters, which is helpful. But it gives no format guidance (e.g., author list format, DOI form, arxiv_id form) and doesn't clarify behavior when both raw_text and structured fields are supplied.

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 verb and resource: 'Verify ONE citation against live scholarly sources (OpenAlex/Crossref/arXiv).' It also distinguishes this tool from claim-support siblings by stating evidence and full-text inputs belong to those tools, not to existence/metadata verification.

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?

It clearly explains the input mode ('either a free-text citation in raw_text, or structured fields') and gives an explicit when-not: evidence/full-text inputs belong to claim-support tools. However, it does not name a specific sibling tool like check_claim_support_tool, only the category, so the routing is slightly less direct.

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