sniff-mcp

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

No annotations are provided, so the description carries full burden. It discloses that the engine answers only from cited Sniff atoms, returns abstained:true if lacking data, never guesses, and is educational not diagnostic. These are key behavioral traits.

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 well-structured and front-loaded with the main purpose, but it is somewhat lengthy. However, every sentence adds value, providing scope, behavior, output format, and usage guidance. Minimal redundancy.

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 complexity of a natural-language QA tool and the presence of an output schema, the description completely covers required information: topics, behavior, output format, and usage boundaries. No gaps are evident.

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 only parameter is 'question' with 0% schema description coverage, but the tool description extensively explains what kind of questions are valid: natural-language canine-genetics questions covering a wide range of topics. This compensates fully for the schema 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 answers natural-language canine-genetics questions with grounded, cited answers. It lists specific topics covered (inherited diseases, breed risks, etc.) and explicitly distinguishes itself from siblings by directing structured lookups to variant/breed/gene 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 provides explicit guidance: 'USE THIS for any 'what is X / does breed Y get Z / human equivalent of W' question; use the variant/breed/gene tools for structured lookups by identifier.' This clearly tells when to use the tool and when to use alternatives.

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 fully discloses behavioral traits: it returns filtered, honest hints, never a confident guess; uses a deterministic query plan; scores by weakest edge; provides evidence tiers; abstains when can't answer; and is hypothesis-generating.

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 verbose but informative; it front-loads key information and uses capitalization for emphasis. While not extremely concise, every sentence 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 the tool's complexity (graph-based, multiple evidence tiers) and the presence of an output schema, the description fully covers purpose, usage, behavior, parameters, and output format, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description compensates well: it explains that 'question' is a free-form cross-species genetics question, and 'narrate=true' provides a one-line prose summary per hint with specific behavior.

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: asking cross-species genetics questions about dog-human diseases, and explicitly distinguishes from sibling tool 'ask' for owner-facing breed/disease queries.

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 guidelines: best for model-discovery and translational traversal, and advises using 'ask' for owner-facing breed/disease/carrier questions.

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 carries full burden. It discloses the tool returns many data types, explains optional breed_context and cross_breed_full behaviors, and notes the default for top_n. It does not mention potential performance considerations or rate limits, but is otherwise transparent.

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 front-loads key information and packs in all details without wasted words. 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 the output schema exists, the description does not need to detail return values. It covers all tool capabilities and parameter behaviors, making it complete for a complex tool with four parameters.

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 fully compensates by explaining all four parameters: position format, breed_context string behavior, cross_breed_full boolean effect (all 188 breeds vs top_n), and top_n default (5). This adds significant meaning beyond the bare 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 returns comprehensive variant data for a CanFam4 position, listing all included fields (frequency, pathogenicity, gene context, diseases, provenance, deep links). It distinguishes from siblings by being the 'headline query' that bundles multiple data types in one call.

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 this tool is for comprehensive variant context, but does not explicitly state when to use alternatives like variant_lookup or breed_variant_frequency. However, the context of sibling tools and the phrase 'headline query' provide clear 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?

No annotations provided, so the description carries full burden. It does not disclose whether the tool is read-only, has side effects, or requires permissions. The metric explanation is helpful but behavioral traits are missing.

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 that packs significant information (type of distance, interpretation). It is efficient and front-loaded, but could be slightly improved by also briefly noting parameter requirements.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description lacks guidance on parameter semantics and does not clarify usage context relative to sibling tools like nearest_breeds. For a tool with no annotations and no parameter descriptions, this is insufficient.

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%, but the description adds no additional meaning for the two parameters (breed_a, breed_b). It does not specify expected format, valid values, or provide examples. Schema only gives names.

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 computes genetic distance using top-10-PC Euclidean and clarifies that lower values indicate more similarity. It distinguishes from siblings like nearest_breeds (which likely finds closest breeds to a single breed) and breed_summary.

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?

Usage is implied for pairwise similarity but no explicit guidance on when not to use it or alternatives. For example, if the user wants to find the closest relatives of one breed, nearest_breeds would be better, but this is not 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?

No annotations are provided, so the description must convey behavioral traits. It indicates a read-only operation (list) but lacks details on data freshness, rate limits, or expected response format, leaving some gaps.

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 that fully communicates the tool's functionality without unnecessary words. It is front-loaded and efficient.

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 has no parameters and an output schema exists, the description adequately covers the tool's behavior (listing breeds with frequencies). No further details are required.

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 parameters with 100% description coverage, so the schema itself is sufficient. The description adds no parameter info, but none is needed, meeting the baseline of 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 uses a specific verb 'list', identifies the resource 'breeds', and specifies the context 'in the atlas' with 'breed-stratified frequencies', clearly distinguishing it from sibling tools like breed_summary or breed_variant_frequency.

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 the tool's purpose (list all breeds with frequencies), but does not explicitly mention when to use it over alternatives. However, the uniqueness of the output (full list) implies its use case.

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 disclosing behavior. It states what the tool returns (variants, count, group) and clarifies that it is descriptive, not a health ranking. However, it lacks details on whether the operation is read-only, if authentication is needed, or how the variant criteria (ESM2, AF) are defined. The output schema exists but is not referenced.

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 concise at two sentences, covering essential information without redundancy. Every phrase adds value: the criteria for variants, the fields returned, and the behavioral caveat. It is well-structured and front-loads the purpose.

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, output schema present), the description covers the main outputs and a key behavioral note. However, it does not define terms like ESM2 and AF, which may be unclear to an agent without domain knowledge. It also does not guide the agent on how the breed parameter is interpreted (e.g., fuzzy matching). While an output schema exists, the description could be more complete within its own text.

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% coverage (no description on the breed parameter), and the description does not elaborate on the expected breed value. It mentions 'Breed profile' but does not specify format, examples, or allowed values (e.g., common name vs. scientific name). This leaves ambiguity for the agent, especially since there are no enums.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool returns a breed profile including top damaging common variants with specific criteria, number of dogs, and breed group. It implicitly retrieves this data, and the additional note 'Descriptive only — not a health ranking' helps distinguish it from health-related tools like disease_bridge or disease_links. However, it could more explicitly name the action verb and differentiate from siblings like breed_variant_frequency.

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 minimal guidance on when to use this tool. The note 'Descriptive only — not a health ranking' hints at a limitation, but it does not explicitly compare with sibling tools such as breed_variant_frequency, breed_similarity, or breeds_in_atlas. There is no advice on when not to use it or what prerequisites exist.

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?

Discloses return format and input constraints. No annotations provided, so description carries full burden. Missing details on behavior when both variant and gene are provided (schema allows both, description says 'either...or').

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 main purpose. Every word adds value. No redundancy or wasted text.

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?

Explains inputs and outputs adequately. Output schema exists (not shown), so return values are covered. Could mention that breed is required and that variant and gene are optional. Minor omission on exclusivity.

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 description adds meaning: explains 'breed' with example, and clarifies 'variant' as variant position and 'gene' as gene symbol. Does not explain default empty strings or mutual exclusivity, but adds value beyond bare 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?

Clearly states it provides breed-stratified allele frequency. Specifies inputs (breed plus variant or gene) and outputs (AF and rank for variant, per-variant AFs for gene). Distinct from sibling tools like variant_lookup or breed_summary.

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 describes when to use: given a breed and either a variant or gene symbol. Does not explicitly state when not to use or compare to alternatives, but the context is clear.

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

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

No annotations exist, so the description carries full burden. It discloses that outputs are atoms with source and atom_id, and states 'Educational, not diagnostic'. However, it lacks details on permissions, rate limits, or behavior when both parameters are provided or empty.

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 structured with an introductory sentence, two clear usage modes, and a closing note about sources. It is reasonably concise, though slightly lengthy. Front-loads the purpose.

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 an output schema exists, the description sufficiently covers main functionality and parameter usage. It lacks explicit handling of edge cases (e.g., both parameters filled), but provides enough context for typical queries. The educational disclaimer adds value.

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 coverage, the description fully explains both parameters: disease accepts a name or OMIA ID, breed accepts an example. It maps each parameter to specific output fields (e.g., disease returns genes, inheritance; breed returns carrier frequency, confidence tier). Examples are provided.

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 provides a fused OMIA disease layer for a given disease or breed, listing specific outputs like genes, inheritance, human homolog, and variant pathogenicity grade. It distinguishes from siblings by mentioning the OMIM/Mondo bridge and breed-specific conditions, which are unique to this 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 implies usage by giving two modes (disease or breed), but does not explicitly state when to use this tool over siblings like disease_lookup or breed_summary. No exclusions or alternative suggestions 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 fully details the tool's behavior: it returns mode of inheritance, causal genes, curated description, phenotype terms, human analog, evidence, and molecular links when available. It also specifies the data source (OMIA) and that it returns a sniff.world URL, plus the educational disclaimer.

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 efficient, covering many aspects in one sentence. It is front-loaded with the core mapping and lists output components. Could be slightly more structured, but is concise given the 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 output schema exists, the description doesn't need to explain return values, yet it does list them. It also adds context about scope (Dog-only) and purpose (Educational, not diagnostic), making it 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?

The sole parameter 'disease' has 0% schema description coverage. The description adds full semantics by clarifying it accepts a disease name or OMIA id, which is sufficient for correct use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool maps a canine inherited disease (by name or OMIA id) to a detailed clinical record, specifying the output components. It also distinguishes itself from the sibling tool 'search_diseases' by noting that tool is for fuzzy candidates.

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 'For fuzzy candidates use search_diseases', providing a clear alternative. Also notes 'Dog-only. Educational, not diagnostic.' which sets proper expectations for when to use this 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?

Describes content of returned record (inheritance, causal genes, etc.), sourcing, and URL. No annotations, but description implies read-only. Could be more explicit about lack of side effects.

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 with no wasted words. Purpose is front-loaded. Includes necessary context and sibling references concisely.

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 presence of output schema, description adequately covers the lookup operation, return content, constraints, and relationships to siblings.

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 no parameter descriptions (0% coverage). Description says query can be disease name or OMIA id, adding meaning beyond the schema. However, lacks format or examples.

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 action (look up), resource (canine inherited disease), and result (OMIA clinical record with details). Distinguishes from siblings by naming search_diseases for disambiguation and disease_links for molecular links.

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 this tool vs alternatives: for candidate disambiguation use search_diseases, for molecular links use disease_links. Also specifies constraint: dog-only.

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 bears full responsibility. It implies a read-only sorted list, but does not state whether it mutates data, requires authentication, or has rate limits. Behavioral traits are under-communicated.

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, short phrase—efficient and front-loaded. However, it is so brief that it sacrifices clarity. Could be slightly expanded without losing 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?

With one parameter and an output schema that is not described, the description fails to explain the output format or pagination. Given the many sibling tools, the agent needs more context to choose this tool for discovery tasks.

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 'limit' has no description in the schema (0% coverage). The tool description does not explain what limit controls (e.g., number of genes returned). Default value of 50 provides some hint, but the agent is left to guess.

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 returns top genes by variant count in the atlas, with a discovery aid purpose. It implies ranking and filtering, but does not explicitly say it lists genes. Sibling tools like gene_summary or variant_search provide different functionality, so this is distinguishable.

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 when-to-use or when-not-to-use guidance is provided. The phrase 'discovery aid' is vague and does not exclude other tools. No alternatives 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?

With no annotations, the description covers pagination (limit, default 25), sorting criteria, and the af_min filter. It does not mention read-only status or prerequisites, but these are implied. The output schema existence reduces the need to detail return fields.

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, compact sentence with no wasted words. It efficiently conveys purpose, ranking, pagination, and filtering options.

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 and the presence of an output schema, the description covers the core aspects: input, sorting, pagination, and a filter parameter. It could mention that gene_symbol must be a valid HGNC symbol, but overall it is 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%, but the description explains all three parameters: gene_symbol (target gene), limit (paginated, default 25), and af_min (global AF filter). This adds meaning beyond the bare 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 the tool retrieves variants for a given gene symbol, ranked by impact then ESM2 damage. This distinguishes it from sibling tools like variant_lookup or variant_search which target specific variants or broader searches.

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 specifies using af_min for filtering, but does not provide guidance on when to use this tool versus alternatives like variant_lookup or variant_search. It lacks explicit context for appropriate use cases.

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 provided, so description carries full burden. Describes returned metadata items but does not disclose any behavioral traits (e.g., read-only nature, rate limits, or caching). Behavior is simple (parameter-less, read-only) but not explicitly stated.

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 sentence listing key metadata items. Front-loaded with purpose. 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?

Tool is simple (no parameters) and has an output schema. Description sufficiently enumerates the type of data returned, making it complete for an overview 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?

No parameters exist, so schema coverage is 100%. Baseline score of 4 applies; description does not need to add parameter meaning.

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 states specific verb+resource: returns Atlas metadata including release, DOI, assembly, variant/breed counts, scope banner, and RPC catalog. Clearly distinguishes from sibling query tools which provide specific data lookups.

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?

Lists what the tool returns, implying use for a general metadata overview. No explicit guidance on when to use or not use versus alternatives; agent must infer from sibling list and context.

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 burden. It reveals the method (PCA-256 Euclidean) but does not state that the tool is read-only or safe. The mention of 'top-10-PC' might mislead about the k parameter's role, but the tool is inherently non-destructive.

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 concise: two sentences with no redundant words. Every phrase adds value, making it optimal for quick agent scanning.

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 output schema exists, return value details are not needed. However, the description lacks parameter descriptions, error handling notes, and clarification on the k vs top-10 discrepancy. It is adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so description must compensate. It barely references parameters: 'given breed' implies the breed parameter, and 'top-10' hints at the default k, but no explicit parameter descriptions or value ranges are provided.

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: finding genetically nearest breeds to a given breed using PCA-256 co-embedding. It answers a specific question and distinguishes from siblings like breed_summary by focusing on genetic similarity, though no explicit 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 description implicitly tells when to use by answering 'what breeds are most genetically similar to X?'. However, it does not provide explicit when-not-to-use guidance or mention alternatives like breed_similarity.

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 provided, so description carries full burden. Discloses output format (ranked candidates with fields omia_id, disease, url, score) and scope. Does not mention side effects, but as a search tool, behavioral transparency 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?

Extremely concise: two sentences, each adding value. Front-loaded with main purpose, followed by usage guidance and scope. 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?

With 2 parameters, output schema present, and sibling tools, the description is largely complete. It specifies the output structure and usage context. Could mention behavior for empty query or error cases, but not critical for a basic search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but description hints at 'free text' for query parameter and implies limit controls ranking size. However, it does not explicitly explain the limit parameter or its default value. Only minimal additional meaning beyond 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?

Clearly states it searches the canine disease catalogue by free text, returning ranked candidates with specific fields. Differentiates from disease_lookup by advising 'Use before disease_lookup when the exact name is unknown.'

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?

Explicit guidance: 'Use before disease_lookup when the exact name is unknown.' Also specifies scope 'Dog-only', indicating the tool is limited to canine diseases. Provides clear context for when to use this tool vs. alternatives.

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?

Without annotations, the description discloses key behaviors: it performs hybrid + semantic ranking, returns ranked entities with snippets and links, and uses OData facets. It does not cover rate limits or auth, but as a read tool this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (about 100 words) and front-loaded with purpose and usage. It flows logically from purpose to parameters to output. Slightly dense but efficient.

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 an output schema exists, the minimal output mention suffices. Parameter explanations are thorough, and usage context is provided. Could enhance with explicit sibling tool differentiation.

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 compensates well: it explains entity_type values (disease|breed|discovery), details filters syntax with examples, and implies query and top_k roles. However, explicit mention of top_k is missing.

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 is a 'Faceted hybrid + semantic-ranker search over the whole knowledge base' with specific examples of fuzzy/thematic intents, distinguishing it from sibling tools like search_diseases or breed_similarity by its broad scope and semantic ranking.

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 provides usage examples for fuzzy/thematic intent but does not explicitly state when not to use it or name alternative tools. The guidance is implied rather than explicit, missing clear differentiation from 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, so description bears full burden. Describes outputs but not behavior on missing variants (error vs null) or input format requirements beyond 'CanFam4 position'. Adequate but not fully transparent.

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 dense sentence with no filler. Front-loads key information: lookup type, coordinate system, and output summary. Every word 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?

With output schema present, description need not detail return structure. Lists output fields adequately. Missing error handling on missing variants, but completeness is strong overall.

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?

Only parameter 'position' has no schema description (0% coverage). Description adds critical context: coordinate system (CanFam4) and lists output fields. However, exact format (e.g., 'chr:pos') is implied but not explicit.

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 'single-variant lookup by CanFam4 position' with a specific verb and resource, distinguishing it from sibling 'variant_search' which handles multiple variants. Output fields are listed, making purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied use case for detailed single-variant lookup, but no explicit guidance on when to use versus alternatives like 'variant_search' or 'ask_variant_context'. Missing 'when not to use' statements.

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 discloses key behaviors: returns total_count plus a capped list (max 200) and a note about popmax breed. With no annotations, this provides essential transparency, though it could mention read-only nature.

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 at three sentences, front-loads the purpose, then lists predicates and return info, and ends with a caveat. 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?

The description covers purpose, filter parameters, return format, and a special note. With output schema present, return values are covered. Minor gap: no explanation of the 'limit' parameter.

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?

Given 0% schema coverage, the description compensates by explaining most parameters (esm_max, phylop_min, popmax_min, gene_in, consequence, impact) with meanings. However, the 'limit' parameter is not described.

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 'Filtered discovery over all 9.67M variants' and lists predicates, making the purpose specific and distinguishing it from sibling tools like variant_lookup.

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 explicitly state when to use this tool versus alternatives like variant_lookup, breed_variant_frequency, or ask. It implies usage for filtered discovery but lacks exclusion criteria or comparative guidance.

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