Folklore Clinical Variant Interpretation MCP

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds substantive behavior beyond that: it preserves conflicting and limited assertions, returns inheritance and snapshot provenance, and clarifies scope limits (not variant pathogenicity, not a diagnosis, requires professional review).

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?

Front-loaded with the core action, followed by return contents and scope limitations in compact sentences. It is slightly long at five sentences, but each carries a distinct point (scope, inputs, outputs, disclaimers), so little is wasted.

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?

An output schema exists, so return-value detail is not strictly required, yet the description still usefully characterizes the payload and its caveats. Combined with the scope-boundary disclaimers, an agent has enough to invoke it correctly, with only alternative-tool routing missing.

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

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

Schema coverage is 100%, so the schema already documents gene, limit, and offset. The description restates the accepted identifier format ('exact gene symbol or HGNC identifier') without adding syntax, constraints, or pagination semantics beyond the schema; baseline 3 applies.

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?

States a specific verb (Find) and resource (diseases associated with a human gene), clearly scoping the direction of the query as gene→disease. It does not explicitly name the reverse sibling (search_disease_genes), so an agent must infer the direction, but the scope 'one human gene' is 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?

Provides research context (bioinformatics and clinical genomics) and constraints ('use only a public gene identifier; no patient or case data'), which implies when the tool applies. However, it never names search_disease_genes or any alternative, nor states when to prefer this over the reverse lookup, so routing is left to inference.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds non-redundant context by noting the data is 'professional literature evidence and contains no patient context,' which is useful for privacy and sensitivity assessment. It also highlights that retraction status is included, a behavioral detail beyond what annotations cover.

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

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

Three tightly written sentences, each earning its place: the first states the action and scope, the second lists return contents, the third gives usage context and safety framing. It is front-loaded with the verb and resource and contains 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?

For a one-parameter, read-only, idempotent tool with an output schema and rich annotations, the description covers purpose, scope, return contents, usage trigger, and data sensitivity. There is no missing information an agent would need 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?

Schema description coverage is 100%: the sole pmid parameter is fully documented with pattern, format, and prefix guidance. The description doesn't add any additional parameter-level semantics, so it does not exceed the 3-point baseline expected when structured schema already covers parameters completely.

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

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

The description opens with a specific verb ('Retrieve') and names a precise resource: 'complete public bibliographic record for one PMID from Folklore's PubMed-derived genetics corpus.' It then enumerates the returned fields (abstract, authors, journal, MeSH terms, gene/variant mentions, retraction status, links), which clearly separates it from the sibling search tools that return sets of results rather than a single record.

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 an explicit trigger: 'Use after literature search when a user asks to inspect a specific publication.' This clearly tells an agent when to invoke it, but it does not explicitly name alternatives or state when not to use it beyond the implied contrast with searching. It is clear context without formal exclusions, so not 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?

Beyond the readOnly/idempotent/non-destructive annotations, it discloses meaningful behavior: name searches can return multiple distinct diseases, the agent must not collapse their identities or infer a diagnosis, and results require professional review. This is exactly the kind of ambiguity and safety context annotations cannot convey.

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

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

The purpose and input mode lead, followed by return content and the important caveats, so the key routing information is front-loaded. Five sentences is on the long side, but nearly all of them carry operational or safety 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?

With an output schema present, parameter documentation complete, and full annotation coverage, the description does its remaining job well by covering input constraints, multi-match behavior and review requirements. The one missing piece is distinguishing this tool from the similarly named get_gene_disease_associations sibling.

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

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

Schema description coverage is 100%, so the schema already documents disease, limit and offset, including the MONDO: seven-digit format and the nextOffset pagination hint. The description adds only a light clarification that results are per-assertion and that name search may fan out, so the baseline 3 applies.

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?

States a specific verb (Find) and resource (human genes associated with a disease), plus the underlying data source (ClinGen gene-disease validity assertions). It does not, however, differentiate itself from the near-identical sibling get_gene_disease_associations, leaving some ambiguity about which to pick.

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?

Gives clear input-side boundaries: 'Use only a public disease name or identifier; no symptoms, patient or case data,' and frames the context (genomic analysis, rare-disease research). It stops short of naming the alternative sibling tool or the conditions that would route an agent there instead.

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, idempotentHint=true, and destructiveHint=false; the description adds meaningful context by stating it returns 'source-linked evidence candidates for professional review, not diagnoses, causality claims or treatment recommendations.' This safety caveat goes beyond the structured 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?

Three sentences front-load the core purpose, provide a concrete usage rule, and close with an important caveat. There is no filler or repetition of schema contents.

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 search tool with a rich output schema and fully documented parameters, the description covers the essential invocation behavior, accepted input classes, and professional-review caveat. It is slightly incomplete only in not routing the agent between overlapping sibling search tools.

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

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

Schema description coverage is 100%, so the input schema already documents query, sort, limit, and cursor well. The description reinforces the query semantics (e.g., PMID/DOI/PMCID as anchors) but adds little parameter-level detail beyond the schema.

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

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

The description names a specific verb and resource: semantically search the public scientific Literature Corpus by natural-language question, and lists accepted identifier/concept types. It is clear on its own, but the title's 'Folklore Literature Corpus' conflicts slightly with the description's 'scientific Literature Corpus,' and it does not explicitly distinguish itself from sibling search_variant_literature.

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 concrete usage guidance: include every known publication identifier when the user wants to compare papers or find work related to a specific paper. It establishes clear context but does not state when not to use this tool versus sibling search tools such as search_variant_literature.

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 cover readOnly/idempotent/openWorld=false, but the description adds real context: it returns normalized identity, ACMG/AMP decision support, evidence, provenance and limitations, is not a diagnosis, and never selects a candidate when resolution is ambiguous. This ambiguity and limitation disclosure goes beyond 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?

Front-loaded with the core action and structured logically, but there is visible redundancy between the opening ('Interpret this variant... review this VUS') and the later 'Use when...' sentence restating classify/interpret/review a VUS.

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 an output schema existing, the description fully frames scope, accepted inputs, what is returned, and explicit limitations (no patient context, not a diagnosis). An agent has everything needed to invoke and interpret 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?

Schema description coverage is 100%, and the schema already documents accepted input forms (coordinates, HGVS, SPDI, rsID, canonical_key). The description largely restates these forms plus the <50bp and single-variant constraints, adding marginal value over the schema.

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

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

States specific verbs (classify, interpret, resolve) and a precise resource and scope: 'one public GRCh38 germline SNV or simple indel smaller than 50 bp.' This clearly separates it from literature-focused siblings like search_variant_literature and search_literature_corpus.

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?

Enumerates concrete when-to-use triggers: classify/interpret pathogenicity, review a VUS, check ClinVar or population-frequency evidence, resolve notation. It does not explicitly name sibling alternatives or state when NOT to use this tool, 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?

The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context beyond the structure: exact variant mentions rank ahead of broader gene associations, and the results should not be interpreted as establishing causality, pathogenicity, or diagnosis. This compounds the tool's behavior beyond what annotations provide.

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 well-structured: the first sentence explains the core function, the second provides usage guidance, and the third adds an important caveat. Every sentence contributes meaningful information and the critical constraints are 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?

Given the output schema, the description does not need to explain return values. It provides the key operational details needed to call the tool correctly: the genome assembly requirement, the ranking behavior, and the clinical classification caveat. It could be slightly more explicit about how gene-level queries are handled, but it is otherwise quite complete for a surgical tool.

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

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

Schema description coverage is 100%, so the schema already documents the query, limit, assembly, and question parameters thoroughly. The description reinforces that query is a variant identifier rather than a natural-language question, but this is also present in the schema's parameter description. The description does not add significant new parameter-level meaning beyond the schema.

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

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

The description states a specific verb and resource: resolve a GRCh38 variant and retrieve publications from Folklore's PubMed-derived corpus. It differentiates itself from sibling tools by focusing on exact variant mentions ranking ahead of gene associations, which clarifies what makes this tool distinct from a general literature 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 description explicitly says to use the tool when a user asks what has been published about a variant, gene, or associated condition. It does not mention exclusions or directly name these siblings, but the context is clear enough for an agent to know this tool is appropriate for variant-centric literature 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?

Annotations already provide readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false. The description adds specific behavioral context beyond these annotations: it explicitly clarifies this is an information action and names precise exclusions (no payment, no relay creation, no result modification). This enriches the agent's understanding of side effects and side-effect-free guarantees, 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 two sentences with no wasted words. The first sentence front-loads the purpose and mechanism; the second sentence immediately addresses exclusions and behavioral boundaries. Each sentence earns its place, and the structure is efficient for agent consumption.

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 parameterless, read-only, informational tool with output schema present, the description covers all necessary aspects: what it does, how it works (via separate MCP), and what it does not do. Annotations handle safety/behavior, and the absence of parameters removes any parameter-related gaps. Nothing material is missing for an agent to correctly invoke this 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 tool has 0 parameters, so the baseline for parameter semantics is 4. The description adds no parameter-specific information because none is needed; the schema is empty and coverage is 100%. The description's focus on purpose and behavioral constraints is appropriate for a parameterless tool.

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

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

The description clearly states the verb 'Learn how an agent can support or spread' and the resource 'Helena's free public scientific infrastructure'. It explicitly identifies the mechanism ('through the separate Helena Good MCP') and distinguishes itself from the sibling search tools by focusing on support rather than search. The sentence 'This is an explicit opt-in information action' further clarifies the tool's nature, removing ambiguity about whether it performs actions.

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 clear exclusions: 'It does not initiate payment, create a relay, or change any Folklore scientific result,' which tells the agent when NOT to use this tool. It also states it is an 'opt-in information action,' implying it should be used when seeking informational support on spreading Helena's infrastructure. However, it does not explicitly contrast with sibling tools or state when to choose it over alternatives, though the context of sibling search tools makes this reasonably clear.

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