raras

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is known. The description adds valuable context beyond annotations with 'Apenas informativo, nunca diagnóstico', clearly stating the tool is not for diagnostic purposes. This is a meaningful behavioral disclosure.

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 short sentences with a clear visual arrow structure, front-loaded with the core purpose. Every word earns its place, 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 tool has three parameters, no output schema, and moderate complexity. The description states the high-level output types and includes a safety disclaimer, but it doesn't explain the effect of the limit parameters or the nature of the returned literature and diseases. Adequate but with notable 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 description coverage is 0%, so the description must compensate. It only indirectly explains case_description via 'Caso clínico', but the limit parameters (papers_limit, diseases_limit) are not addressed in either the schema or the description. The parameter names are suggestive, but the description adds no clarity about how they affect the output.

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 uses a clear arrow structure 'Caso clínico → doenças candidatas + literatura relevante' which explicitly states the transformation from clinical case to two outputs. It distinguishes itself from sibling tools by emphasizing the combined result 'em 1 chamada', though it doesn't explicitly name alternatives.

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 phrase 'em 1 chamada' implies this tool is used to get both diseases and literature in a single call, but no explicit when-to-use or when-not-to-use guidance is provided. The caveat 'Apenas informativo, nunca diagnóstico' offers a usage restriction but no alternative tool suggestions.

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 and closed-world semantics, but the description adds crucial behavioral details: it refuses when no graph path exists and never fabricates evidence. This goes beyond the structured annotations and is highly valuable for an agent.

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: first sentence states the function, gives examples, and describes the output; second sentence states the refusal behavior. No filler 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?

With read-only and closed-world annotations plus an output schema, the description covers the core behavior, refusal mode, and typical use cases. The only notable gap is the lack of explanation for the optional parameters, but the tool is still quite complete for selection and basic 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 explains the query parameter via natural-language examples, but says nothing about hpo_ids or max_hops, leaving two of three 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 clearly states the tool performs graph-grounded reasoning and returns multi-hop evidence paths with citable provenance. Concrete examples ('why does gene X associate with disease Y?') make the scope unambiguous and distinguish it from sibling tools like get_evidence or get_hypotheses.

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: use when a natural-language question requires multi-hop explanation over the graph, with representative question formats. It does not explicitly name alternatives or exclusions, so it stops short of a 5.

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 of behavioral disclosure, but it says nothing about side effects, return types, pagination, filtering behavior, or required permissions. It is essentially non-informative about behavior.

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 very short, but this is under-specification rather than good conciseness. It lacks key information and does not front-load useful context; the few words used are vague and partially redundant with the tool name.

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 3 parameters (one required), no output schema, and no annotations, the description is entirely insufficient. It fails to explain what the tool returns, how parameters affect results, or any practical usage context, making correct invocation nearly impossible.

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 does not compensate. 'Brazil filter' vaguely hints at in_brazil_only, but there is no explanation of orphaCode, limit, or the interaction between parameters. The agent is left without meaningful 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 'Trials ativos com filtro Brazil' is a fragment with no clear verb, essentially restating the tool name 'find_active_trials' and adding an ambiguous 'Brazil filter' reference. It does not specify what the tool does (e.g., find, list, search) or what the output represents.

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?

There is no guidance on when to use this tool versus alternatives. The sibling tools (e.g., find_reference_centers, find_phenotypically_similar) are not mentioned, and no context or exclusions are 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It reveals nothing about side effects, output format, permissions, pagination, or any constraints. The description is essentially a label with no behavioral insight.

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 extremely short, but this is under-specification rather than conciseness. It is a vague fragment with an apparent typo ('FEBRARARAS') and no structured information. There is no useful content that 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 2 parameters, no output schema, and no annotations, the description must provide substantial context. It fails to explain the tool's purpose, result format, or how parameters are used. This is completely inadequate for an agent to 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 0%, yet the description provides no parameter details. It does not explain what 'orphaCode' represents or what 'limit' controls. The schema itself has only type/constraint metadata, leaving the agent without meaningful 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 'Comunidades FEBRARARAS por doença' is a noun phrase rather than a clear action statement. It restates the concept of 'communities' from the tool name/title and adds an unclear modifier ('FEBRARARAS') plus 'by disease' without specifying the actual operation. It does not distinguish from sibling tools like find_reference_centers or find_active_trials.

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 usage guidance is provided. The description does not indicate when to use this tool, what scenarios it applies to, or how it differs from alternatives. There is no mention of exclusions, prerequisites, or context for selecting this tool over siblings.

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, and the description gives no behavioral details such as whether the operation is read-only, what the output looks like, or any side effects. It only states the input and a use case.

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 short sentences, each serving a purpose. It is front-loaded with the main function and adds a use case. However, it is very terse, which impacts completeness rather than conciseness.

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 tool has a 2-parameter schema with no output schema or annotations. The description fails to explain what the tool returns, how to interpret results, or the function of the limit parameter. It does not provide enough context for an agent to use it effectively.

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 mentions HPO IDs as the main input, aligning with the hpo_ids parameter, but it does not explain the limit parameter at all. Given 0% schema description coverage, this is insufficient.

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 'Match por IDs HPO' indicates the action (match) and input (HPO IDs), and the title clarifies it searches diseases. It is clear enough but relies on the name for the resource. It distinguishes from siblings by focusing on HPO ID matching and differential diagnosis.

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 phrase 'Use para diagnóstico diferencial' provides a clear use case (differential diagnosis), but it does not explicitly mention alternatives or 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.

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

Annotations are absent, so the description carries the full burden. It only mentions the retrieval method (embeddings, semantic match) but doesn't disclose output format, ranking behavior, score thresholds, or read-only nature. Minimal behavioral insight beyond the name.

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 concise sentence, front-loaded with the core purpose. It is efficient and structurally clear, though overly terse, which limits its informational value.

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 no annotations, no output schema, and 3 parameters, the description is too sparse to be complete. It doesn't cover return values, parameter usage, or how to choose this over sibling tools, leaving the agent under-informed 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%, and the description does not explain any parameters. The disease input (orphaCode) is implied, but limit and min_score are left unexplained. The description adds no value over 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 states it finds literature related to a disease using embeddings (:SEMANTIC_MATCH, fallback vetorial). The verb 'find' and resource 'literature' are clear, and the disease context is implied. It doesn't explicitly distinguish from sibling search_papers_semantic, but the 'for_disease' scope adds 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?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention when not to use it or which sibling tools serve different purposes (e.g., search_papers_semantic for general paper search).

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 the tool as read-only and closed-world, and the description adds meaningful context about the underlying algorithm (precomputed simGIC) and how similarity is explainable (number of shared phenotypes). This goes beyond what annotations provide and helps set expectations about the kind of results, though it does not mention any rate limits, pagination, or result ordering.

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, front-loaded with the core purpose, and every word earns its place. The first sentence delivers the essential function, and the second provides a crisp comparison with a sibling tool, with no redundant content.

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 presence of an output schema and read-only annotations, the description covers the main behavioral context well, including the similarity metric and how it differs from a sibling tool. It is slightly incomplete because it does not specify that the input is a disease's Orpha code or clarify how the limit parameter behaves, but the schema partially covers these details.

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, and the description does not explain the meaning of orphaCode or limit beyond what the schema already shows. The description's mention of shared phenotypes hints at the similarity calculation, but it does not compensate for the lack of parameter explanation, leaving the agent to infer that orphaCode is a disease identifier and limit caps results.

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 as finding diseases with similar HPO phenotype profiles, using a precomputed simGIC metric and an explainable count of shared phenotypes. It explicitly distinguishes itself from the sibling tool find_similar_diseases, which is semantic-based, so the purpose is specific and non-ambiguous.

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 states that this tool complements find_similar_diseases (semantic), giving the agent a clear clue about when to choose this phenotypic/explainable approach over the semantic one. It stops short of explicitly stating 'use this when you need precomputed phenotypic similarity' or 'do not use when semantic similarity is needed', but the alternative is named and the distinction is evident.

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 of behavioral disclosure. It mentions that CNES is included in results, but gives no information about return format, filter behavior (whether filters are optional, combine with AND/OR), or data source specifics. The fragment is too sparse to inform an agent about side effects or data shape.

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 extremely short (six words) with no wasted text. It is a single compact phrase, which is efficient for conciseness, though the lack of sentence structure limits the amount of information conveyed. The brevity earns a high score for conciseness, but the content is not fully 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 3 parameters, no annotations, and no output schema, the description is insufficient. It does not explain what the tool returns (list vs. detail), how filters interact, what CNES is, or when to use it over similar lookup tools. The description gives only a vague context, leaving significant gaps for an agent to invoke it 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?

The description maps 'doença' to orphaCode and 'UF' to state, providing meaning that is not in the schema. However, 'limit' is not mentioned at all, and the schema has 0% description coverage. The partial explanation of two of three parameters adds moderate value but doesn't fully compensate for the missing limit 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 'Centros por doença e/ou UF, com CNES' identifies the resource (reference centers) and two filter dimensions (disease, UF), but lacks an explicit verb like 'find' or 'list'. It doesn't clearly distinguish from sibling search tools beyond implying filtering by rare disease code and state.

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. There is no mention of appropriate scenarios, required context, or how filters combine (e.g., AND/OR semantics). This is a bare statement of content, not usage direction.

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 of behavioral transparency, yet it only mentions an embedding technique and the ambiguous acronym 'SOTA'. It does not disclose whether the operation is read-only, how the input is used, what the output contains, or any constraints, providing essentially no behavioral information.

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 extremely short, but this is under-specification rather than good conciseness. 'Vector similarity via embeddings SOTA' is cryptic and does not effectively communicate the tool's function in a structured way.

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 tool with no output schema and no annotations, the description is severely incomplete. It does not explain what the tool returns, how similar diseases are scored, or provide any context for interpreting results, making it impossible for an agent to use 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 0%, and the description does not compensate by explaining orphaCode or limit. The agent is left with only parameter names and basic constraints, making it difficult to understand what values are appropriate or how they affect the search.

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 'Vector similarity via embeddings SOTA' is vague and method-oriented rather than a clear statement of the tool's purpose. It does not explicitly say that the tool finds similar diseases, leaving the agent to infer from the name. It also fails to distinguish the tool from siblings like find_phenotypically_similar, which likely uses a similar vector-based approach.

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 offers no guidance on when to use this tool versus alternatives such as find_phenotypically_similar or search_diseases. It does not mention the input orphaCode, typical use cases, or any exclusions, leaving the agent without context for tool 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 burden of behavioral disclosure. It only lists data fields returned, but does not describe side effects, read-only nature, error behavior, or authorization requirements. This is minimal content disclosure rather than behavioral 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 a single, concise sentence listing five key content types with zero filler. It is front-loaded and every word adds value. The comma-separated structure is easy to parse, making it appropriately sized for the level of detail.

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 moderate complexity (returns multiple types of information) and lack of annotations/output schema, the description is incomplete. It does not state the required input, output format, or any constraints. The agent lacks essential context to use the tool effectively, especially without usage or parameter guidance.

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 schema has one parameter (orphaCode) with 0% description coverage, and the description does not explicitly explain the parameter's meaning. It indirectly implies that the code identifies a disease by mentioning 'doença rara' and listing disease-related data, but the agent is left to infer that orphaCode is the disease identifier. No format or example is given.

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 lists the specific content types (HPO phenotypes, genes, SUS, trials, clinical description in PT), which clearly indicates the tool retrieves a comprehensive detail view for a rare disease. The name and title reinforce the purpose, and the list distinguishes it from sibling tools that focus on subsets (e.g., get_sus_coverage, find_papers_for_disease). However, the description lacks an explicit verb like 'retrieves', relying on the tool name for action clarity.

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. It does not mention use cases, prerequisites, or exclusions. Sibling tools exist for specific aspects (e.g., find_similar_diseases, get_sus_coverage), but no comparison or selection criteria are 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?

Annotations already indicate readOnlyHint=true, and the description adds behavioral context by specifying the exact data sources and the 'never invent' principle, which signals the tool is authoritative and should be trusted for evidence. It does not contradict annotations and adds useful context about the tool's role in grounding factual claims, though it does not mention pagination or 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?

The description is two sentences long, front-loaded with the primary function and followed by a short rationale. Every word earns its place, with no redundancy or fluff.

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 simple input (one required parameter), the presence of an output schema, and the readOnly annotation, the description sufficiently covers the tool's purpose and content. It does not need to explain return structure due to the output schema, and the 'never invent' phrase adds contextual value. The only minor gap is explicit usage boundaries, which is already addressed in the usage dimension.

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 schema has one parameter, orphaCode, with 0% coverage in the description. The description says the tool returns evidence 'of a disease,' implying the input is a disease identifier, but it does not explicitly explain that orphaCode is the Orphanet code. Since there is only one parameter and its name is self-descriptive, the description provides adequate if minimal semantic 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?

The description clearly states the tool retrieves evidence/provenance for a disease, listing specific authority databases (Orphanet, MONDO, OMIM, MeSH, GARD, UMLS) along with verification status and PMIDs. It distinguishes itself from siblings like get_disease_detail by focusing on cross-references and verification, though it lacks an explicit action verb like 'retrieves' or 'returns'.

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 the tool: it provides authoritative cross-references and is 'the basis of the never invent rule,' suggesting it should be used to ground disease facts. However, it does not explicitly mention alternatives or when not to use it, so guidance is implicit rather than explicit.

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 of behavioral disclosure, but it only states 'counts and metrics' without mentioning return format, side effects, performance, or other behavioral traits. It implies a read-only operation but does not explicitly confirm this.

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, concise phrase that is immediately understandable. It is front-loaded with the key information with 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?

The tool is simple with no parameters, but the description does not specify which metrics are included or what 'dataset' refers to in the graph context. It is minimally sufficient but leaves ambiguity about the exact content of the statistics.

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 tool has zero parameters, so parameter semantics are trivially satisfied. The description need not add parameter details, and the baseline for 0-parameter tools is 4.

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 'Contagens e métricas do dataset' clearly indicates the tool provides counts and metrics for the dataset, which is a specific output. However, it lacks an explicit verb and does not differentiate from sibling tools beyond the name.

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 given on when to use this tool versus the many sibling tools. The description does not mention any context, constraints, or alternatives, leaving the agent without direction.

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 readOnlyHint annotation, the description discloses that results are generated via guilt-by-association, are hypotheses only, and are traceable via gene and disease. This adds meaningful behavioral context without contradicting the 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 a single, dense sentence that efficiently conveys purpose, method, and caveat. It avoids unnecessary fluff while packing essential 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?

For a read-only, single-parameter tool with an existing output schema, the description provides strong contextual completeness: it explains what the tool does, how results are generated, and the crucial caveat that they are hypotheses. The only minor gap is the implicit parameter 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?

The input schema has zero description coverage, but the description implies the 'orphaCode' parameter refers to the disease in question via 'compartilham genes com esta.' This is not explicit, so the parameter semantics are only partially addressed.

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 returns drug repositioning candidates generated by gene association (guilt-by-association), and explicitly distinguishes these as hypotheses, not clinical recommendations. This specificity differentiates it from sibling tools like get_evidence or find_similar_diseases.

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 the tool is for investigating drug repositioning hypotheses and includes a strong warning that results are never clinical recommendations. However, it does not explicitly state when to use this tool versus alternatives or 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?

Annotations already supply readOnlyHint and openWorldHint, so the description's burden is lower. It adds that the tool returns typed relations with publication counts and is filterable by predicate, but it does not disclose behaviors like pagination, data update frequency, or result limits. This is modest extra value 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-loading the main function (typed relations extraction) and then adding the filter capability. No wasted words 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?

Given the moderate tool complexity and the presence of an output schema and annotations, the description sufficiently covers the essential semantics: disease-to-gene/drug relations, predicate filtering, and publication counts as provenance. It leaves out minor details like specific predicates already in the schema, but the overall picture is complete for an 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?

With 0% schema description coverage, the description must explain parameters. It implies orphaCode is a disease identifier and explains predicate as a filter, listing several predicate values. However, it omits two enum values from the schema and does not explicitly state that predicate is optional, so the coverage is incomplete.

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 function: it retrieves typed relations from biomedical literature between a disease and genes/drugs, specifying the predicate types and provenance (number of publications). This distinctly separates it from siblings like find_papers_for_disease or explain_relation, which focus on papers or explanations.

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. There is no comparison with sibling tools, no recommended context, and no exclusions. The only usage hint is 'filterable by predicate,' but that is a feature rather than a usage directive.

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 the description adds behavioral context: it lists the types of evidence that count as updates and highlights the stateless polling nature. This goes beyond the annotations by clarifying the criteria for inclusion and the non-persistent behavior.

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 concise sentences: the first states the core purpose, the second explains the usage as a polling substitute. Every word contributes value, and the main function is front-loaded.

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 two optional parameters, an output schema, and read-only annotation, the description adequately covers purpose, usage, and parameter context. Minor gaps like sorting or pagination details are not essential given the output schema.

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 is the only source for parameter meaning. It explicitly mentions 'N dias' corresponding to the 'days' parameter, giving context for the time window. However, it does not explain 'limit' beyond its name, leaving minimal semantic assistance for that parameter.

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 specifies the tool's purpose: listing diseases whose digital twin has gained new evidence (authorship, PubTator3, Open Targets, verification) within N days. This names the resource (disease twins) and the action (recent updates), distinguishing it from sibling tools like get_disease_detail or get_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 explicitly instructs using this tool for polling to track changes, calling it a stateless substitute for subscriptions. This provides clear when-to-use guidance, though it does not explicitly name alternatives or exclusions.

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 the description adds useful context about the content (agent's actions, chronological order). However, it does not disclose behavioral nuances like pagination, potential size of the log, or that the log may be empty for new diseases. It does not contradict annotations; the added value is moderate.

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 sentence, front-loaded with the core concept 'Registro cronológico' (chronological record). It lists relevant content areas and a purpose statement, all without unnecessary verbosity. Every phrase adds value.

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 that an output schema exists to describe the return format, the description provides enough context about what the log contains and its purpose. It covers the agent's activities and the chronological aspect. It could mention ordering direction or absence of filtering, but such details are likely in the output schema or not essential for this simple one-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?

The schema has one required parameter, orphaCode, with 0% description coverage. The description mentions 'por esta doença' (for this disease), which implicitly ties the parameter to a disease identifier, but it does not explicitly define orphaCode's meaning or format. Since the parameter name is self-explanatory and the description gives a hint, the gap is partially compensated but not fully.

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 explicitly states that the tool provides a chronological record of what the autonomous agent did for a specific disease, listing the types of activities (e.g., authorship, literature mining, genetic evidence). This clearly identifies the resource and distinguishes it from sibling tools that focus on disease data or evidence rather than the agent's research process.

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 does not specify when to use this tool over alternatives. It implies the log serves as proof of the digital twin's study, but it does not provide explicit context, such as 'use this to audit agent activity' or 'for actual evidence, use get_evidence.' No exclusions or alternatives are mentioned.

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, so the agent knows it is a safe read operation. The description adds minimal behavioral context beyond the schema contents (e.g., that it should precede cypher_query). No contradictions, but also no additional details about rate limits, auth, or exact response format. Given the simple nature of the tool and existing annotations, this is adequate.

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 short sentences, front-loaded with the purpose and followed by a clear usage directive. There is no waste, and every word earns its place. The mix of English and Portuguese is concise and understandable.

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 (no parameters, no output schema), the description is sufficiently complete: it names the schema elements and gives usage context. It could explicitly state the return format, but that is implied by 'Node labels, relationship types e property keys'. The 'Use antes de cypher_query' provides important workflow context, making the description effective for an AI 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?

The tool has zero parameters, so the description does not need to explain parameter meanings. The baseline for 0 parameters is 4, and the description appropriately focuses on what the tool returns rather than any parameter details.

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 states what the tool returns: 'Node labels, relationship types e property keys do grafo' (graph schema components). It clearly identifies the resource (graph schema) and differentiates it from sibling tools, which focus on queries, diseases, papers, etc. However, it lacks an explicit verb like 'return' or 'get', relying on the tool name for the action.

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 explicit usage guidance: 'Use antes de cypher_query' (Use before cypher_query), telling the agent when in the workflow to invoke this tool. It does not mention alternatives or exclusions, but for a schema-retrieval tool, the ordering guidance is highly relevant and 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?

No annotations are provided, and the description discloses no behavioral traits—no mention of what is fetched, side effects, return format, or safety profile. The description is merely a fragment.

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 very short, but the brevity is due to under-specification rather than conciseness. It is a cryptic list of terms that does not form a complete, informative sentence.

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 tool has a single parameter, no output schema, and no annotations. The description provides almost no context, making it impossible for an agent to infer what the tool does, what input is expected, or what results are returned.

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 schema has one required parameter 'orphaCode' with a digit pattern, but the description gives no explanation of what this parameter represents or how to use it. With 0% schema description coverage, the description fails entirely to compensate.

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 title 'Cobertura SUS' suggests the tool deals with SUS coverage, but the description 'CEAF, SIGTAP, PNTN, nível de integração' is just a cryptic list of acronyms without a verb or stated action. It does not clearly say what the tool does and fails to distinguish itself from siblings like get_disease_detail.

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?

There is no guidance on when to use this tool versus alternatives. No context, prerequisites, exclusions, or references to sibling tools are 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?

With no annotations, the description must carry the full burden. It discloses the core behavior (full-text search with filters) and the corpus size, but does not mention output format, pagination, read-only status, or any side effects. For a search tool, this is minimally adequate but lacks depth.

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 the core purpose and followed by a brief note on filters. Every word earns its place; there is no redundancy or fluff.

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 tool has 4 parameters, no output schema, and no annotations, so the description needs to provide more context about expected results and parameter behavior. It omits what the return value looks like, how limit works, and any constraints like minimum query length, making it insufficient for a complete understanding.

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 explicitly mentions the SUS and trials filters, and 'full-text search' implies the query parameter. However, the 'limit' parameter is not addressed in the description, and the schema provides no descriptions either, leaving a gap.

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 performs full-text search over a specific set of 10,468 rare diseases, and mentions the SUS/trials filters. This specific verb+resource+scope distinguishes it from sibling tools like find_diseases_by_phenotypes or search_phenotypes.

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 usage for searching rare diseases when SUS coverage or active trial filters are needed, but it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. The filter support gives context, but no direct comparison to siblings.

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 full responsibility for behavioral disclosure. It only mentions 'vector search' and the corpus size, but does not clarify read-only status, return format, ordering, pagination, or any side effects. This is a significant gap for a tool with no annotation support.

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 short sentences, front-loaded with the core purpose. No wasted words, and all content is relevant.

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 annotations, no output schema, and 0% parameter coverage, the description is too sparse. It should clarify result format, parameter effects, and any operational behavior to be considered complete for a tool of this 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?

The schema has 0% description coverage, so the description must compensate. It gives guidance for the 'query' parameter (clinical case, question, symptoms) but completely omits explanation of 'limit' and 'min_score'. This partial coverage is insufficient.

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 a specific action: 'Busca vetorial sobre 424k papers do PubMed' (vector search over 424k PubMed papers). It distinguishes from sibling search tools by specifying the corpus and the semantic nature of the search.

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 second sentence provides explicit usage context: 'Use caso clínico, pergunta ou conjunto de sintomas' (use clinical case, question, or set of symptoms). This indicates when to use the tool, though it does not explicitly mention alternatives or exclusions.

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 behavioral burden, but it only discloses language support and return of HP IDs. It does not explain matching behavior, case sensitivity, pagination, or how the limit parameter affects results.

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 concise sentence, front-loaded with the action and resource. It is efficient but arguably too sparse to be fully helpful.

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 2-parameter search tool with no output schema or annotations, the description provides only the bare minimum. It lacks details on expected query format, return structure, and behavioral nuances, making it inadequate for reliable tool 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 coverage is 0%, and the description does not explain the 'query' parameter beyond the implicit HPO context. It does not clarify whether query accepts an HP ID, a term in PT or EN, or both, and it omits the 'limit' parameter entirely.

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 performs an HPO lookup in Portuguese or English and returns HP IDs, distinguishing it from sibling tools that search diseases or papers. However, it could be more explicit about being for phenotypes.

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 given on when to use this tool versus alternatives like find_phenotypically_similar or search_diseases. There is no mention of appropriate use cases or exclusions.

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