SiteCheck Health & Travel

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds valuable non-structured context: the x402 pricing model ($0.002 USDC per successful call, failed calls not charged) and payment rails. It stops short of describing pagination or list ordering, but the pricing disclosure is meaningful.

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 front-loaded sentences: scope and categories, return fields, then filters and pricing. The category enumeration is long but earns its place by defining coverage. Minimal waste.

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 values are covered, and the description still names the key fields. Combined with full schema coverage and annotations, an agent has enough to call it correctly; only pagination/ordering behavior is unaddressed.

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 all five parameters are already documented with defaults and examples (e.g., state code 'TX', country code 'USA'). The description's 'filter by state, country or name' restates the schema rather than adding syntax or constraint detail, so 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?

The description opens with a specific source (AABB public lists) and enumerates the exact facility categories covered, plus the per-facility fields returned. An agent can tell instantly this is an AABB accreditation lookup and distinguish it from CLIA laboratory finder or provider registry siblings.

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 states the available filters ('Filter by state, country or name'), which implies usage, but gives no explicit when-to-use guidance or comparison against the nearest sibling (e.g., health_clia_laboratory_finder). The usage is inferred rather than directed.

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 readOnly/openWorld, but the description adds genuinely non-structured behavior: a $0.002 USDC charge per successful call via x402, with failed calls not charged, and a 50-row ceiling. That payment model materially affects invocation decisions. It stops short of noting data recency or which years are actually populated.

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?

Four compact sentences, front-loaded with what the data is, then the caveat, the limit, and the price. No filler; every clause carries information an agent would act on.

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 values need no explanation, and the cost/row-limit guardrails are covered. Minor gap: no indication of available year range or what happens when the state name doesn't match the dataset spelling, which matters for a single required 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?

Schema description coverage is 100%, so each of max/year/state is already documented with types, defaults and examples. The description only echoes "by US state and year" and adds the rate unit, providing no syntax or format detail 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+resource: "CDC/NCHS leading causes of death by US state and year", plus the exact metrics returned (cause, deaths, age-adjusted death rate per 100,000). It also distinguishes itself from the CDC WONDER query tool, so the agent knows this is the published table, not the queryable database.

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 context (data.cdc.gov open data, published table, not the WONDER query tool) and a hard operational limit of 50 rows per call. It does not, however, route the agent among the many sibling health datasets (e.g. fluview or WHO stats) that could plausibly be confused with mortality data.

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 only declare readOnlyHint and openWorldHint; the description goes well beyond by disclosing the paid model ($0.002 USDC per successful call, x402 on Base/Solana/Arc) and that failed calls are not charged — critical invocation context an agent cannot get from structured fields. It also names the upstream data provider, which matters for result trustworthiness.

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?

Purpose and lookup modes are front-loaded, then return fields, then pricing — a sensible order with no filler. The long enumeration of returned fields is partly redundant with the existing output schema, which keeps it from being maximally tight.

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 lookup with a full output schema and complete parameter descriptions, the only thing the description must add is provenance and the payment requirement — both are covered explicitly, including the no-charge-on-failure guarantee.

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 every parameter already carries its own description and example values (MCF-7, CVCL_0031, ACH-000019). The description restates those same key formats without adding semantics the schema lacks, 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 and resource (cancer cell line lookup) plus the authoritative source (Cellosaurus), and enumerates the three lookup keys (name, CVCL accession, ACH DepMap ID) and the disease-list mode. No sibling tool in the list covers cell lines, so an agent can immediately tell this is the only relevant option.

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 maps each mode to its input: find by name/accession/DepMap ID, or list DepMap-linked lines for a disease, and the schema example ('breast carcinoma') reinforces the disease mode. It gives clear usage context but does not state exclusions or point to any alternative resource.

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 and openWorldHint. The description adds useful behavioral context beyond that: result cap of 20 per call, total match count, per-call pricing, payment methods, and that failed calls are not charged.

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 definition is appropriately brief and front-loads the search purpose, followed by limits and pricing. The list of returned fields is somewhat dense but still serves to orient the caller.

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 complete parameter schema coverage, an output schema, and safety annotations, the description provides enough context to invoke the tool correctly. The main missing piece is sibling differentiation, which is scored separately under usage guidelines.

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 both q and max are fully documented in the input schema. The description does not add further semantics about the query syntax or how matching works, so the baseline 3 is appropriate.

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

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

The description states a specific verb and resource: "EMBL-EBI ChEMBL molecule search," and lists the main result fields. It is clear what the tool does, but it does not distinguish itself from sibling chemical tools such as health_pubchem_chemical_cid or health_drugbank_interaction.

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 no explicit guidance on when to use this tool versus alternatives, such as PubChem, DrugBank, RxNorm, or other ChEMBL-related searches. Usage is only implied by the name and description.

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 mark it read-only and open-world, while the description adds useful behavioral context: data source freshness, a 50-lab cap, pricing, payment networks, and that failed calls are not charged. It does not detail error cases beyond failed-call charging, but the disclosure is substantially richer than the annotations alone.

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

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

The description is front-loaded with source and scope, then adds fields, exclusion, cap, and pricing with little wasted text. The first sentence is dense, but every element provides useful selection or invocation context.

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 read-only lookup, the description covers source, geography, returned fields, exclusion, per-call limit, and payment behavior. Output schema exists and annotations cover safety traits, so no critical context is 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 description coverage is 100%, so state and max are already fully documented. The description reinforces the state scope and the 50-lab cap but adds no syntax or format detail beyond the schema, making 3 the appropriate baseline.

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 resource (CMS CLIA-certified clinical laboratories) and scope (one US state), plus the exact fields returned. It lacks an explicit action verb and does not name a sibling alternative, so it is clear but not fully differentiated.

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 by the one-state scope and the note that tests performed are not listed, which helps exclude a related need. However, it gives no explicit when-to-use/when-not guidance and names no alternative tool for test-level laboratory data.

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?

Goes well beyond the annotations by disclosing the x402 payment model, price ($0.002 USDC per successful call), accepted chains, and that failed calls are not charged — critical cost/behavior context for an agent. Also caps result volume at 10 per call and clarifies the record type is citation-only.

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 compact sentences, resource and provenance front-loaded, followed by scope limits and pricing. No filler or repetition; every clause carries information an agent needs.

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 paid, read-only evidence lookup with an output schema present, the description covers source, record contents, per-call cap, and cost/charging behavior. Nothing material is missing 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 coverage is 100%, so the parameter meanings (search terms, count range 1-10, default 5) are already documented in structured fields. The description's 'for a search term' and 'Up to 10 per call' restate rather than enrich the schema, so 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 resource (Cochrane systematic reviews via PubMed, journal Cochrane Database Syst Rev) and enumerates exactly what each record contains (PMID, title, publication date, DOI). 'Citation records only (no abstract, no full text)' cleanly separates it from siblings like health_pubmed_abstracts without requiring schema inspection.

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 context for when this is the right source: intervention evidence, Cochrane-filtered, search-term driven with a 10-per-call cap. The limitation 'no abstract, no full text' implicitly routes agents elsewhere for full text, but no sibling is named explicitly as an alternative.

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 only declare readOnlyHint and openWorldHint; the description adds substantially more — per-call cost ($0.002 USDC), the payment rails (x402 on Base, Solana, Arc), and the fact that failed calls are not charged, which materially affects an agent's retry calculus. It also caps result volume per call.

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 front-loaded sentences cover purpose, scope limit, volume, and cost with no filler. The pricing clause is dense but every element (amount, currency, rail, failure policy) is decision-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?

An output schema exists, so return-value shape needn't be explained, and the description still summarizes the fields. With only two parameters, full schema coverage, and explicit cost and scope statements, an agent has everything needed to decide and invoke correctly.

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

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

Schema coverage is 100%, so both 'gene' and 'max' are already documented with format constraints and the 1–20 range. The description's 'Up to 20 guidelines per call' restates the schema's 'max' bound rather than adding syntax or edge-case guidance. Baseline 3 applies when the schema carries the parameter burden.

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?

Names a specific source and resource (CPIC pharmacogenetics guidelines) keyed on a gene symbol, and enumerates what comes back (guideline name, genes covered, version, ClinPGx link). It is clearly distinct from adjacent siblings like health_clinvar_genetic_variants or health_gwas_catalog_associations, though it never names an alternative explicitly.

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 guidelines only; recommendation text is not included' is an explicit boundary that tells an agent when this tool will not satisfy a request for dosing recommendations. It also states the 20-per-call ceiling, so a caller knows to paginate or narrow. No named substitute tool for the recommendation-text case, which keeps it 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?

Annotations already declare readOnlyHint and openWorldHint, but the description adds genuinely new behavior: a hard 10-per-call cap, per-call cost of $0.002 USDC via x402 across three chains, and that failed calls are not billed. That billing/failure policy is exactly the kind of thing annotations cannot express.

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 dense sentences, front-loaded with the identity of the resource, then field list, then limits and pricing. No filler, and every clause carries information an agent needs.

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, the description needn't explain return structure, and annotations cover the read-only profile. It also states the cap and cost, covering the main operational risks. A minor gap is not mentioning rate limits or pagination beyond the 10-item cap.

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 both parameters are already documented in the schema with ranges and defaults. The description only restates the max=10 ceiling; it adds no syntax guidance for the free-text search term. Baseline 3 is appropriate.

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

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

Names a specific verb and resource ('ClinicalTrials.gov study search (API v2)') and enumerates the returned study fields, so an agent knows exactly what it retrieves. It does not explicitly contrast itself with neighbors like health_pubmed_abstracts or health_clinical_evidence_cochrane, which is the only thing keeping it off a 5.

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 by the search-term hint (condition, drug, sponsor) and the 10-study cap, but there is no explicit when-to-use / when-not-to-use statement or named alternative. The agent must infer that this is the registry lookup rather than a literature or systematic-review source.

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 openWorldHint=true, so the description does not need to restate safety. It adds meaningful behavioral context: up to 10 variants per call, omission of variant names and protein changes, and a clear pricing model where failed calls are not charged.

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

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

The description is front-loaded with the core resource and returned fields, then adds limits, exclusions, and pricing in compact sentences. Every sentence carries operational value for an agent deciding whether and how to call the tool.

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 two-parameter schema, full schema coverage, annotations, and the existence of an output schema, the description is complete for correct invocation. It covers scope, output content, limits, exclusions, and payment behavior without needing to explain return-value structure.

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 both the gene and max parameters are already documented in the schema. The description reinforces the gene-symbol scope and the one-to-ten limit but adds no new syntax or edge-case semantics beyond that baseline.

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 resource (NCBI ClinVar variants), the key input (human gene symbol), and the returned fields (VCV accession, variant type, germline clinical significance, last evaluation date). It clearly differentiates this clinical-variant lookup from sibling health tools such as dbSNP, GWAS, or pharmacogenetics.

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 by 'for a human gene symbol' and by the stated limits, but the description does not explicitly say when to choose this tool versus alternatives like health_dbSNP_polymorphisms or health_gwas_catalog_associations. It gives useful constraints but no direct routing guidance.

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/openWorldHint annotations, the description discloses non-obvious behavior: a hard cap of 'Up to 20 rows per call' and a paid x402 cost model ($0.002 USDC per successful call, failures not charged) — critical context an agent cannot get from annotations. Return-format detail is left to the output schema.

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 what the tool returns, then filters, then limits and pricing. Dense but every clause carries information; only the pricing clause is slightly outsized for a tool description.

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, full parameter coverage and annotations already present, the description supplies the remaining operationally important facts (row cap, cost, filter combinations). Minor gaps around result ordering and whether filters are ANDed are the only omissions for an open-world, 4-parameter tool.

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

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

Schema description coverage is 100%, so each parameter is already documented in the schema. The description adds the mutually exclusive framing of npi vs generic and the 20-row ceiling, but nothing about formats beyond the schema's '10-digit NPI' note — consistent with the baseline 3.

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 ('CMS Medicare Part D prescriber rows (by provider and drug)') and enumerates the returned fields (NPI, name, specialty, state, drug, claims, fills, cost). This clearly separates it from generic provider-registry or drug-label siblings.

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 explicitly names the two access paths: 'Filter by 10-digit NPI, or by generic drug name with an optional state,' which tells an agent how to combine parameters. It stops short of stating when to prefer this over siblings like health_npi_provider_registry or health_fda_orange_book.

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 read-only and open-world behavior, yet the description adds material context the annotations cannot: a paid model ($0.002 USDC per successful call), payment rails, and the guarantee that failed calls are not charged. It also discloses the data source and a deliberate coverage gap (CIR omitted), which prevents wrong expectations.

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?

A single front-loaded paragraph that leads with purpose and payload, then exclusions, then pricing. Dense but every clause carries information; only the field enumeration is mildly redundant given the output schema exists.

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 annotations and an output schema already present, the description supplies the remaining decision-critical facts: source authority, excluded CIR content, and cost model. Nothing needed to invoke it correctly is missing, though the return-field list is a slight duplication of 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 100%, so both the required INCI name and the limit (1–25, default 10) are already fully documented in structured form. The description reinforces that lookup is keyed on INCI name but adds no syntax, matching, or ambiguity-resolution detail beyond the schema, so 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+resource ('Cosmetic ingredient lookup by INCI name') and enumerates the returned fields (functions, chemical description, CAS/EC numbers, CosIng ID) plus the authoritative source (EU CosIng). It also explicitly distinguishes itself from the sibling health_eu_cosing_cosmetics, so an agent can route without opening either schema.

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 names the boundary case (CIR safety assessments not included) and routes to the alternative sibling for EU restrictions. Clear context for when to pick this over the EU restrictions tool, though it gives no guidance on the analogous chemical-identity tools such as pubchem_chemical_cid.

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?

Goes well beyond the readOnly/openWorld annotations: discloses a 50-site cap per call, an explicit price ($0.002 USDC per successful call), the x402 payment rails (Base, Solana, Arc), and that failed calls are not charged. The dataset-limitation caveat adds interpretive guardrails an agent could not get from structured 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?

Three dense sentences, front-loaded with the resource and scope; each carries distinct payload (what it returns, what it is not, cost/limits). No filler or hedging.

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 only two parameters, full schema coverage, an output schema, and readOnly/openWorld annotations, the description supplies the remaining non-obvious essentials: cost model, cap per call, and the pathogen ambiguity. Nothing an agent needs to call it correctly is 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 description coverage is 100%, so both 'state' and 'max' are already documented with format and range. The description's 'Up to 50 sites per call' only restates the schema's max bound and adds no new parameter meaning; 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+resource: CDC NWSS wastewater sampling sites in one US state, and enumerates the returned fields (plant, county, population served, detection proportion, percentile, sample dates). The dataset-of-origin note (data.cdc.gov) further narrows it apart from siblings like health_fluview_influenza_cdc or health_cdc_wonder_mortality.

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 caveat that 'the pathogen is not named in the dataset; this is not confirmed COVID-19 activity' discourages a common misreading and implies when the tool is appropriate. However, it never states when to prefer it over a sibling (e.g., fluview for influenza surveillance) or any prerequisite beyond the required state parameter.

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 and openWorldHint, yet the description adds genuinely non-obvious behavior: a per-call cost of $0.002 USDC settled via x402 on Base, Solana or Arc, with failed calls not charged, plus a hard cap of 20 codes per call. That payment/auth detail is exactly the kind of context annotations cannot carry. It stops short of describing failure modes or empty-result behavior, so not a 5.

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 compact sentences: what it searches and returns first, the critical scope exclusion second, the operational limits and pricing last. No filler, nothing repeated from the name or annotations.

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

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

With a 2-parameter schema at full coverage, an output schema, and read-only annotations, the description covers the remaining agent-relevant facts: source provenance, CPT exclusion, result cap, and cost. Missing only edge-case behavior such as zero-match handling or whether `term` is substring vs. token matching.

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 both `term` and `max` are already documented in the schema. The one addition — 'Up to 20 codes per call' — reinforces the `max` ceiling but adds no new syntax or format guidance beyond the schema's '1 to 20 (default 10)'. Baseline 3 is appropriate.

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

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

States a specific verb and resource ('HCPCS Level II billing code search'), names the authoritative source (CMS code set via NLM Clinical Tables), the covered domain (procedures, supplies, drugs), and what is returned (code, short description, total match count). The explicit exclusion of AMA-licensed CPT codes draws a clean boundary that separates it from other coding tools like health_icd10_cm_diagnosis or health_loinc_laboratory_codes.

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 scope statement ('HCPCS Level II... procedures, supplies and drugs') implies when the tool applies, and the CPT exclusion tells the agent when it does not apply. But no alternative tool is named for the CPT or diagnosis-code case, and there is no explicit 'use this when...' routing guidance among the many health coding 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?

Goes well beyond the readOnly/openWorld annotations by disclosing result cardinality (up to 10 labels per call), the payment mechanism and cost ($0.002 USDC per successful call via x402 on Base/Solana/Arc), and that failed calls are not charged — a critical caveat for an agent deciding whether to retry. The explicit statement that section text is excluded prevents misreading the return payload.

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, each load-bearing: what is returned, what is not returned, cardinality, then price/charging semantics. Scope and limits are front-loaded before the billing footnote.

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

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

With a 2-parameter schema, an output schema, and readOnly annotations, the only remaining agent-relevant unknowns would be result caps and cost — both are stated explicitly. Nothing needed to invoke this correctly is 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 both parameters are already documented, including the 1-10 range and default 5 for 'max'. The description only reinforces the 10-label cap and drug-name matching, adding no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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

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

States a specific verb and resource: NLM DailyMed drug label listings (structured product labeling) matched by drug name, and enumerates the returned fields (title with labeler, set ID, version, published date, match count). The sentence 'Lists labels only; label section text is not included' cleanly separates it from full-text drug resources and from sibling identifiers/registries like health_rxnorm_concept_id or health_fda_orange_book.

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 context is clear: call it when you have a drug name and want label metadata. The explicit exclusion of label section text tells the agent when this tool is not sufficient. It does not name an alternative sibling for full label text or interactions, 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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses two meaningful traits: a hard result cap ('Up to 10 frequency rows per call') and the billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). That is real operational context an agent needs before calling. It stops short of describing rate limits or what a not-found rs id returns.

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, no filler: the data payload is front-loaded and the cost/result-cap sentence follows. Slightly compressed — the pricing clause bundles currency, rails, and failure policy into one dense phrase, but nothing 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?

For a single-parameter read tool with an output schema and read-only annotations, the description covers the essentials (data returned, result cap, cost model). The main residual gap is error behavior for invalid or unknown rs identifiers, which matters for a paid per-call endpoint.

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 one parameter and schema coverage is 100%, with the schema itself supplying the rs-number format and an example (rs429358). The description adds no additional constraint or format guidance for rsid beyond restating 'by rs number', so the baseline of 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+resource: retrieves the NCBI dbSNP short variant record for an rs number, and enumerates exactly what the record contains (variant type, sequence placement, ref/alt alleles, allele frequencies). This is clearly distinguishable from genomic siblings like health_clinvar_genetic_variants or health_gwas_catalog_associations, which the dbSNP naming and field list set apart.

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 only implied by the field list (you'd call this when you need variant identity and population allele frequencies). There is no explicit when-to-use statement, no guidance on choosing dbSNP over ClinVar/GWAS Catalog, and no exclusions or prerequisites for the rs-number lookup other than the modifier 'short variant'.

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 openWorldHint=true. The description adds valuable context beyond that: pricing model ($0.002 USDC per successful call via x402, failed calls not charged), data source (eCFR), search limitation (only table entries, not paragraph entries), and result cap (up to 20 matches per call). This is a solid behavioral disclosure, though it stops short of describing return values or pagination behavior (which the output schema presumably covers).

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 with semicolons, front-loaded with purpose and scope. Every clause earns its place: data source, return fields, search limitations, exclusions, result cap, and pricing. It is efficient, though slightly crammed and could be marginally more readable with sentence breaks.

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 (a read-only lookup with a complete input schema, output schema, and annotations), the description covers the essential context: what it returns, what it excludes, data source, result cap, and cost. Nothing critical is missing for an agent to call 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%, so both parameters are fully documented in the schema. The description adds a small amount of context ('matching a name' and 'Up to 20 matches per call' relating to the max parameter), but does not meaningfully extend parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description states a specific verb (returns/lookup) and resource (DEA controlled substance schedules, 21 CFR 1308.11-1308.15), and specifies exactly what data is returned: substance name and DEA Controlled Substances Code Number for schedule I–V table entries matching a name. It distinguishes from siblings because no sibling covers DEA controlled substances.

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

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

The description gives useful scope limitations (e.g., 'Substances listed only in paragraphs are not searched' and 'Does not include registration status'), which help an agent understand when the tool will not work. However, it does not explicitly say when to use this tool versus alternatives, nor does it name any alternative tools.

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

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

Annotations already establish readOnly and openWorld, so the description's added value is the payment model: $0.002 USDC per successful call via x402 on Base/Solana/Arc, with failed calls not charged. That pricing and failure-billing detail is materially useful before an agent spends money, though it doesn't describe response shape or paging behavior (both covered elsewhere).

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?

Purpose and source scope are front-loaded, and the payment terms are placed last where they belong. The middle field enumeration (issue, renewal, expiry, sedation permits, controlled-substance licenses) is dense and partly duplicates the output schema, slightly bloating a one-sentence description.

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 agent knows which states and license types are available, which search keys work, that active licenses are default, and what the call costs. With a full schema and an output schema in place, nothing needed to call it correctly is 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 description coverage is 100%, so the schema already documents all eight parameters including the state enum values and the activeOnly default. The description only restates the search axes and the active-by-default rule, adding little beyond structured data. Baseline 3 is appropriate.

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

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

States a specific verb and resource ('Dental license verification') and immediately scopes it to two named official sources (Colorado, Illinois) with the license subtypes covered. This cleanly separates it from the medical-board, nursing, and veterinary license siblings, which cover different professions.

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?

'Search by license number, name or city; active by default' tells the agent the three supported lookup modes and the default filter behavior. It stops short of naming alternatives (e.g., use health_state_medical_board_* for physicians or health_nursing_licensure_nursys for nurses), leaving that routing to inference from the profession names.

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 only declare read-only and open-world, so the description carries the rest and does: source (openFDA label text), explicit limits (no severity, absence != no interaction), and a billing model ($0.002 USDC per successful call via x402, failures not charged). The cost and charge-on-success detail is exactly the kind of operational context an agent needs before calling.

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-loads what the tool returns and where it comes from, then limits, then price. Dense but nearly every clause carries decision-relevant information; the pricing sentence is long but necessary given the x402 payment model.

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, the description need not explain return shape, and it covers source, caveats and payment. It does not say what happens with multiple matches or how sentences are chosen, a minor gap for a matching tool.

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

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

Schema coverage is 100% and both parameters already document the A/B roles, name format and length. The description reinforces the directional semantics (search A's label for B) and points at the interactions section specifically, but adds no syntax or normalization guidance beyond the schema, 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+resource: matching sentences from drug A's FDA label drug-interactions section that mention drug B, plus the returned fields (label set ID, effective date). The scope is narrow enough that an agent can distinguish it from label-lookup or adverse-event siblings without opening the schema.

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 a clear usage caveat that prevents misuse: a no-match result does not mean no interaction exists, and this is label text only with no severity score. It does not point to any alternative tool (e.g. a severity-scored interaction source) for that case, so it stops short of full when-to-use/when-not guidance.

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 and openWorldHint, so the description adds valuable context beyond that: data freshness (updated twice a day), pricing ($0.002 per successful call via x402), and the result cap of 20 per call. It also clarifies that failed calls are not charged, which is useful behavioral detail for a paid tool.

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 tightly front-loaded with the resource and data fields, followed by search behavior and pricing. Every sentence carries useful information with no redundancy or wasted words.

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

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

Given the presence of an output schema, the description need not explain return values. It covers the data source, fields available, search input, result limit, and cost model, which is complete for an agent to call it correctly. Annotations already cover safety, so no further behavioral disclosure is 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?

Schema description coverage is 100%, so the schema already documents both parameters in detail (q: name or active substance, letters/digits/spaces, 2–60 chars; max: 1–20, default 5). The description only restates that it searches name or active substance and caps results at 20, adding little 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 (searches) and resource (EMA centrally authorised human medicines) with a clear scope and data fields. It is clearly distinct from sibling health_ema_shortages_safety by focusing on the medicines registry rather than shortages, but it does not explicitly differentiate itself from that or other sibling tools.

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

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

The description implies usage by stating 'Searches name or active substance' and 'Up to 20 per call', which signals a lookup tool. However, it gives no explicit when-to-use vs alternatives guidance, no exclusions, and no prerequisites beyond the payment model.

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 only declare readOnlyHint and openWorldHint, but the description adds substantial operational context the agent otherwise could not know: a hard cap of 20 results per call, a per-call price of $0.002 USDC, the payment rails (x402 on Base, Solana or Arc), and that failed calls are not charged. Cost and failure-billing behavior are exactly the kind of disclosure that matters for a paid tool, so this exceeds the annotation baseline.

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 resource and its fields, then the exclusion, then limits and price; nothing is padding. The three-sentence block is dense but slightly overloaded, with the payment-rail parenthetical ('Base, Solana or Arc') adding bulk that could be terser.

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, single-resource lookup with an output schema and readOnly/openWorld annotations, the description covers everything needed to call correctly: data domain, exclusions, result cap, and cost model. Return-field documentation is delegated to the existing output schema, which is the right split.

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 both parameters are already documented with types and constraints (q: 2–60 chars, medicine or INN words; max: 1–20, default 5). The description echoes the result cap ('Up to 20 per call') and characterizes the query domain as medicine/INN but adds no syntax, matching behavior, or default beyond the schema. Baseline 3 is appropriate.

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

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

Names a specific verb/resource (EMA human medicine supply shortages) and enumerates exactly what the record contains: medicine, INN, shortage status, affected forms, alternatives, start and expected resolution dates. It also disambiguates against its own misleading name and against nearby siblings by stating 'Shortages only; safety signals and pharmacovigilance data are not included' — an agent can immediately tell this apart from health_ema_human_medicines or safety/pharmacovigilance sources.

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 a clear negative scope boundary (no safety signals, no pharmacovigilance), which prevents a common misuse. However, it never names an alternative tool or states a positive condition such as 'use this for EU shortages; use health_fda_drug_shortages for US'. Usage is implied by scope rather than prescribed.

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 establish that this is a read-only, open-world lookup. The description adds meaningful behavioral context beyond the annotations: pricing at $0.002 USDC per successful call, payment via x402 on Base/Solana/Arc, and the fact that failed calls are not charged.

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 definition is dense but front-loads the core purpose and regulatory scope before the pricing detail. The long first sentence is justified by the complexity of the regulatory coverage, and the pricing sentence is short and useful.

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 and annotations, the description provides a complete enough picture: what is looked up, which regulatory annexes are covered, what fields are returned, and how billing works. The main remaining gap is sibling differentiation, which is a minor omission for a read-only lookup 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 both parameters are already documented in the schema. The description reinforces that the lookup is by substance name and describes the regulatory entries returned, but it does not add syntax or constraints beyond what the schema provides; baseline 3 is appropriate.

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

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

The description states a specific resource and scope: EU cosmetics regulatory status from CosIng, including the exact annexes and Regulation (EC) No 1223/2009. It is clear what the tool returns, but it does not explicitly distinguish itself from the sibling health_cosmetics_inci_ingredients 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?

There is no explicit guidance on when to use this tool versus alternatives, nor any stated prerequisites or exclusions. The use case is implied by the description of regulatory status lookup, but the agent is left to infer when this is preferable to the related cosmetics INCI 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real value on top: a hard cap of 10 reports per call, the x402 payment rails (Base, Solana, Arc), the $0.002 per-successful-call charge, and that failed calls are free. It does not mention data recency/lag or FAERS coverage window, which keeps it short of a 5.

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?

Roughly four sentences, front-loaded with the resource and return fields, then caveat, then cap, then price. Every sentence carries distinct information with no repetition of the title.

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 lookup with an output schema already defining the payload, the description supplies everything an agent needs: input constraint, result cap, causal-interpretation caveat, and the cost/payment model before the call is made.

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 both parameters are already documented in the schema. The description reinforces the 'generic drug name' constraint and the 10-report ceiling but adds no syntax, normalization, or format detail beyond what the properties already state; 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?

Names a specific verb and resource (FDA FAERS drug adverse event reports via openFDA) and enumerates the returned fields (report ID, receive date, seriousness, patient age/sex, drugs, reactions). It also fixes the input domain to a generic drug name, which cleanly separates it from siblings like health_drugbank_interaction or health_fda_recalls_enforcement.

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 constrains the query to a generic drug name and warns that spontaneous reports do not prove causation, which implies appropriate interpretation. However, it never states when to prefer this over alternatives (e.g., EMA or drugbank sibling tools) or any prerequisites beyond the payment note.

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 read-only, open-world behavior, but the description adds information none of the structured fields carry: a per-call price ($0.002 USDC), the x402 payment rails (Base, Solana, Arc), and the crucial billing nuance that failed calls are free. That cost/auth profile is exactly the kind of behavioral context an agent needs before invoking a paid endpoint.

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 tight sentences: identity and returned fields first, the lookup constraint second, pricing last. No filler, and the most decision-relevant facts (DI-only, cost) are surfaced early.

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?

A single required parameter, 100% schema coverage, existing output schema, and annotations covering safety profile mean the description only needs to add scope and cost — both are present. Nothing an agent needs to call this correctly is 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% and the schema itself defines 'di' as 8–14 digits, so the baseline is 3. The description earns above baseline by explaining what the identifier physically is (the GS1/GUDID number printed on a device label), helping the agent supply the right value rather than a product name.

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?

Names the specific dataset (FDA AccessGUDID), the exact lookup key (Device Identifier / GS1-GUDID label number), and enumerates the returned fields (brand, company, model, GMDN term, MRI safety, sterile/single-use flags). The negative scope 'Lookup by DI only; no name search' separates it from name-based device searches such as the 510k sibling.

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?

Clearly states the only supported access path (by DI) and explicitly excludes name search, which prevents the most likely misuse. It does not route the agent toward a specific alternative (e.g., 510k clearance lookups) or state prerequisites, so it stops short of full when/when-not guidance.

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 and openWorldHint, but the description adds real value: a hard cap of 10 listings per call and a pricing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failed calls uncharged). It does not describe pagination or auth/setup beyond the payment rail.

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 the resource and its source, then fields, cap, and cost. Slightly redundant given the output schema exists and already covers returned fields, but the enumeration aids tool selection.

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 output schema covers return values and annotations cover safety, so the description need only add scope, cap, and cost — which it does. Missing only sibling routing advice for EU versus US shortage data.

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 both parameters (q, max) are fully documented in the schema. The description only echoes them ('generic name', 'up to 10 listings per call') without adding syntax, matching behavior, or format guidance, so the baseline of 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+resource: FDA drug shortage listings from openFDA, and enumerates the returned fields (generic name, availability status, manufacturer, package NDC, posting dates, contact). The 'FDA/openFDA' framing separates it from health_ema_shortages_safety implicitly, but no sibling is explicitly named.

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 explicit when-to-use, when-not-to-use, or alternatives. The closest sibling, health_ema_shortages_safety (EU shortages), is never mentioned, so an agent must infer geographic scope on its own. Usage is only implied by the field listing.

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 only declare readOnly/openWorld, so the description earns credit for adding the operational facts an agent needs: a hard cap of 10 results per call, a $0.002 USDC charge per successful call via x402 on Base/Solana/Arc, and that failed calls are free. This is material for deciding whether to invoke a paid tool; it stops short of describing rate limits, latency, or matching 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 tight sentences: the first front-loads what data comes back, the second front-loads the cap and cost. Nothing is repeated from structured fields (aside from the cap) 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?

With an output schema present and 100% parameter coverage, the description needs only to add cost, cap, and scope, all of which it does. The remaining gap is the absence of routing guidance against the many neighbouring health_fda_* tools, which an agent must infer from the name alone.

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 both parameters (q, max) are already fully documented in the schema, and the description only echoes the 1-10 cap. Baseline 3 applies since the description adds no new syntax, matching semantics, or default guidance 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?

Names the exact regulatory resource (FDA 510(k) premarket notifications via openFDA) and enumerates the returned fields (K-number, device name, applicant, decision, dates, product code, advisory committee), which separates it from siblings like health_fda_device_gudid, health_fda_recalls_enforcement and health_fda_orange_book. It opens with a noun phrase rather than a verb ('Search/Retrieve'), so the action itself is only implied.

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 statement of when to use this tool versus the many adjacent FDA/device siblings, and no exclusions (e.g. 'use gudid for device UDI lookups, this for premarket clearances'). The 'Up to 10 per call' note describes a cap, not usage guidance.

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 only cover readOnly/openWorld, but the description adds the operationally decisive context an agent needs before spending money: a hard cap of 10 applications per call and a $0.002 USDC charge per successful call via x402 on Base, Solana or Arc, with failed calls not billed. Cost, payment rails and billing failure semantics are exactly the traits 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?

Two sentences, no filler: resource and filter first, then limits and price. Each clause carries distinct information (source, key, returned fields, cap, cost, billing exception) with nothing repeated from the title.

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, return-field details are technically redundant but harmless, and the pricing/limit coverage makes the definition self-sufficient for invocation. Minor gap: no note on how partial or zero matches behave (e.g. ingredient not found, brand-name input rejected), which matters for a paid per-call 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% — both 'ingredient' (letters/spaces, 2-60 chars) and 'max' (1-10, default 5) are fully documented in the schema. The description reinforces the ingredient key and the 10-per-call ceiling but adds no format or matching nuance beyond that, 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?

The description names a specific source (FDA Drugs@FDA / openFDA) and a specific filter key (active ingredient), then enumerates the returned fields (application number, sponsor, brand names, dosage form, marketing status, TE code). That is enough for an agent to distinguish it from adjacent drug tools, though it never explicitly contrasts itself with siblings like health_fda_purple_book or health_drugbank_interaction.

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 only implied by the phrase 'by active ingredient' — there is no explicit statement of when to choose this over the other FDA/EMA/drug-reference siblings, nor any exclusion or prerequisite (e.g. exact ingredient spelling, generic vs brand). An agent must infer the routing decision itself.

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 openWorldHint=true, so the safety profile is clear. The description adds valuable context beyond annotations: it discloses the pricing model ($0.002 USDC per successful call via x402, failed calls not charged) and the data source ('FDA's monthly Purple Book data download'), which helps an agent understand cost and data freshness. Minor gaps remain around matching semantics (exact vs. partial) and error behavior, but the added context is substantial.

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

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

The description is front-loaded with the core purpose and is generally well-structured. However, it enumerates many return fields ('applicant, BLA number, license type... exclusivity expiry dates') that are already documented in the output schema, making it longer than necessary. The pricing sentence is useful but the overall paragraph could be tighter given the structured fields available.

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 tool with two parameters and a full output schema, the description covers the essential context: what data is returned, where it comes from, and the cost model. It does not explain matching behavior (exact vs. partial name matching) or handle formatting for the 'name' parameter beyond an example, but these are minor gaps given the annotations and output schema already provide safety and return structure.

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 both parameters ('name' and 'limit') with types and constraints. The description adds an example ('adalimumab') and clarifies that 'name' can be a brand, proper name, or BLA number, but this largely restates the schema. With full schema coverage, baseline 3 is appropriate.

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

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

The description states a specific verb and resource: 'FDA Purple Book licensed biological products matching a name'. It enumerates the exact fields returned (applicant, BLA number, license type, etc.), which clearly distinguishes it from siblings like health_fda_orange_book (drugs) and health_fda_adverse_events_faers. An agent can immediately tell this is for biological product licensing data.

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 saying 'matching a name (brand or proper name, e.g. adalimumab)', but it never states when to use this tool versus alternatives such as health_fda_orange_book or health_ema_human_medicines. There are no explicit exclusions or alternative-routing instructions, leaving the agent to infer the appropriate 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?

Annotations only say read-only and open-world; the description adds material behavior the agent cannot get elsewhere: a hard cap of 10 results per call and a pay-per-call model ($0.002 USDC via x402 on Base, Solana, or Arc) where failed calls are not billed. That pricing detail is critical pre-invocation context. It stops short of describing result ordering or what counts as a 'failed' call.

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 paragraph, front-loaded with what the tool returns, then scope, then limits, then pricing — a sensible order with little waste. Slightly compressed but every clause carries 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 an output schema present, the description need not explain return shape, and it still names the key fields; pricing and call limits, the two things an agent must know before invoking, are covered. Nothing needed for a correct call is 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 both parameters are already documented in the schema. The description only restates the 'product word' matching concept and the 10-result cap, adding minimal meaning beyond the schema's own 'letters and spaces, 2 to 60 characters' and '1 to 10 (default 5)' notes. 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 and resource ('FDA drug recall enforcement reports matching a product word') and lists the fields returned, so an agent knows exactly what it retrieves. It also scopes the domain with 'Drug recalls only, not food or cosmetics,' which separates it from other FDA dataset siblings, though it doesn't name a sibling tool by 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?

The exclusion clause 'Drug recalls only, not food or cosmetics' tells the agent one clear case where this tool is wrong, which is genuine usage guidance. However, no alternative tool is named for the out-of-scope cases and no prerequisites (e.g. query format expectations) are given beyond the schema.

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 mark this read-only and open-world, and the description goes well beyond them: it discloses metered pricing ($0.002 USDC per successful call via x402 on Base/Solana/Arc) and, crucially, that failed calls are not charged — decisive information for an agent weighing call cost. It also bounds the query window to 12 weeks.

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?

Purpose and scope are front-loaded in the first clause, and the pricing caveat is appended as a single efficient sentence. The parenthetical about Delphi Epidata is slightly parenthetical-heavy but earns its place by establishing provenance/mirroring.

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, return values needn't be spelled out, yet the description still enumerates them. Combined with region/range rules and cost behavior, an agent has what it needs to call correctly; only edge cases (invalid epiweek handling, error responses) are left unstated.

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%, and all three parameters carry their own descriptions ('nat' or 2-5 letter state code, YYYYWW format, 12-week span), so the schema already does the heavy lifting. The description restates the 12-week range limit but adds no format or semantics beyond the schema; baseline 3 is appropriate.

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

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

The description names a specific verb ('weekly ILI and weighted ILI') and a specific resource/dataset ('CDC FluView', served via Delphi Epidata), plus the exact fields returned (epiweek, ILI %, weighted ILI %, patient/provider counts). No sibling in the list covers FluView ILI data, so an agent can route here unambiguously.

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 gives the operative constraint ('Give an epiweek range of up to 12 weeks') and a scope exclusion ('No outbreak maps'), which is meaningful for an agent deciding whether this tool fits. It stops short of naming an alternative tool for outbreak maps or for non-epiweek resolutions, so it is clear context rather than full when/when-not guidance.

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 and openWorldHint, but the description adds substantive behavior: data provenance (CMS monthly formulary files), freshness (includes CMS release date), year scope, and a pay-per-call price with failed calls not charged. The payment model is critical context an agent would otherwise miss; it lacks only detail on latency or result size.

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-loads what the tool is and what it returns, with pricing correctly appended last. The long field enumeration is dense but each item earns its place; the description is a single run-on sentence plus a payment sentence with little 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?

For a read-only open-world lookup with an output schema (returns needn't be explained), the description covers source, year scope, query modes, key outputs, freshness, and payment terms. Nothing an agent needs to call it correctly is 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 all five parameters. The description adds meaning by showing how 'plan', 'state', and 'limit' correspond to the different query modes and by clarifying year scope, but does not go beyond what the schema describes for individual parameters.

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 (lookup), resource (Medicare Part D formulary coverage), and enumerated outputs (tier, PA, step therapy, quantity limit, cost share, premiums). The field list makes it unmistakable versus generic siblings like health_cms_medicare_part_d or health_rxnorm_concept_id.

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?

Clearly frames the three query modes (one plan via 'plan', state listing via 'state', or every formulary) and notes year coverage (current and next plan year), giving the agent a scaffold for choosing parameters. It stops short of naming alternatives or when-not-to-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?

Goes well past the readOnly/openWorld annotations: metadata-only with no sequence payload, a hard 10-record cap per call, per-call pricing in USDC via x402 across three chains, and the explicit refund behaviour that failed calls are not charged. Payment/auth mechanics and cost are exactly the kind of context annotations cannot carry.

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 tight sentences, front-loaded with the resource and returned fields, followed by input capability, limits, and cost. No filler and nothing repeated from the schema verbatim.

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?

Output schema exists, so the field list is a bonus rather than a necessity; the description still covers scope, input flexibility, call-size limit, and billing model. Nothing an agent needs before invoking a paid, open-world search is 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% and already documents both params and the 1-10 range, so baseline is 3. The description adds real value on top by giving a concrete accession example (NM_000546) and broadening 'term' to gene names and arbitrary NCBI search expressions, which the schema's character-class description does not convey.

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?

Names the exact database and record type (NCBI GenBank nuccore), then enumerates the returned fields (accession with version, title, length, organism, molecule type, update date) and explicitly rules out sequences. That specificity separates it from neighbouring bio-database siblings such as dbSNP, ClinVar or UniProt without needing to name them.

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?

Tells the agent what kinds of input are accepted (accession, gene, or any NCBI search term) and the 10-record cap, which implies the search use case. But it never says when to prefer this over dbSNP/ClinVar/PubMed, nor what to do if a term is too broad or returns nothing.

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 only declare read-only and open-world behavior; the description adds important operational context: $0.002 per successful call, x402 payment on Base/Solana/Arc, and failed calls are not charged. It does not cover rate limits or auth beyond payment, so it is strong but not fully exhaustive.

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 front-loads purpose and returned fields, then adds constraints and cost. Every sentence contributes useful selection or invocation information, with no redundant restatement of the 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?

An output schema exists, annotations cover safety/open-world behavior, and the parameters are fully documented. The description adds the essential search limitation, result cap, and payment model, leaving no major gap 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 100%, so the gene and max parameters are already well documented. The description reinforces the mapped-gene restriction and the 1-10 result cap, but adds little parameter-level syntax beyond what the schema provides.

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 gives a specific resource (EMBL-EBI GWAS Catalog genome-wide association hits) and scope (for a gene symbol), and lists the returned fields. It clearly distinguishes this from generic biomedical siblings by naming GWAS Catalog associations and mapped-gene 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?

It states a clear usage constraint ('Searches by mapped gene only') and a cap ('Up to 10 hits per call'). However, it does not explicitly name when an agent should use an alternative sibling such as ClinVar or dbSNP for variant-centric queries.

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 only declare readOnlyHint and openWorldHint; the description adds genuinely non-obvious behavior: a paid call ($0.002 USDC via x402 on Base/Solana/Arc) with the important caveat that failed calls are not charged, plus a data-coverage limit (federal-platform states). These are exactly the operational facts an agent cannot infer from structured 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?

Front-loaded with the resource and data source, then scope limit, then pricing; no filler sentences. The long enumeration of return fields is slightly redundant given an output schema exists, though it usefully signals what decisions the tool supports.

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 lookup with full schema coverage and an output schema, the description covers source, coverage limits, and payment mechanics thoroughly. The only gap is what an agent should expect for ZIPs outside federal-platform states (empty result vs. error), which a caller would want to know.

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 baseline is 3, but the description adds real meaning by explaining that premiums are reported for the 'nearest published age' rather than the exact age supplied — a non-obvious rounding rule. It says nothing about the optional county FIPS parameter's role when a ZIP spans counties, which keeps it shy of a 5.

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 resource (ACA Marketplace / HealthCare.gov QHP Landscape data) and scope (a US ZIP code), and enumerates the concrete outputs: plan and insurer counts, plans per metal level, cheapest plan per tier, and the benchmark silver plan. No sibling tool covers ACA marketplace plans, and the description makes that boundary obvious.

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 a clear applicability constraint — 'Federal-platform states only' — which tells the agent when this tool will not work, and implicitly frames usage as ZIP-level ACA shopping. It does not name any alternative for non-federal-platform states or for adjacent needs (formulary or Medicare lookups), so exclusions are stronger than routing.

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/openWorld annotations, the description discloses important behavior: the dataset scope, newest-100 cap, total open cases, per-call price, accepted payment networks, and that failed calls are not charged. This is exactly the kind of operational context an agent needs before invoking a paid data tool.

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

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

The description is front-loaded with the resource and scope, then filters, then pricing. Despite being dense, every clause carries useful information and there is no filler.

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

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

With an output schema present, the description need not explain return values, and it covers scope, filters, and payment sufficiently for invocation. It could be slightly more complete about pagination or default row count, but the schema supplies those 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?

Schema description coverage is 100%, so the input schema already documents every parameter, including the limit range and defaults. The description mentions the main filters but does not add syntax or meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description identifies a specific dataset, the HHS OCR HIPAA breach portal, with clear scope (500+ individuals, last 24 months, under investigation) and enumerates the returned fields. This distinguishes it from the many other health-data siblings without ambiguity.

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 gives clear context for when the data applies, including the 24-month window, investigation status, and available filters. It does not explicitly name when to prefer a sibling tool or when not to use this one, so it stops short of full routing guidance.

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 state readOnlyHint=true and openWorldHint=true. Beyond that, the description adds meaningful operational context: the x402 payment requirement, the charge per successful call, that failed calls are not charged, and the per-state result cap. It does not detail authentication mechanics beyond payment, but it adds substantial value over 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 front-loads the data source and returned fields, then appends the cap and pricing. Every clause is relevant, though the semicolon-heavy list is less scannable than it could be.

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 and annotations covering safety and openness, the description supplies the key remaining context: data source, returned fields, per-state limit, and payment model. It is nearly complete, missing only explicit alternative selection 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?

Schema description coverage is 100%, so both parameters are already documented in the schema. The description reinforces that 'max' is bounded and applies per state per call, but does not add syntax or constraints beyond what the schema already states. Baseline 3 is appropriate when the schema does the heavy lifting.

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 identifies a specific resource (CMS Hospital General Information from data.cms.gov) and enumerates the fields returned, including overall star ratings and measure counts. It is clear what the tool does, though it does not explicitly distinguish itself from sibling CMS tools such as physician_compare_cms or medicare_advantage_star.

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 by the dataset focus and the 'up to 50 hospitals per state per call' constraint, but there is no explicit when-to-use guidance or naming of alternative sibling tools. The pricing note helps with cost decisions but does not route the agent among competing health data tools.

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

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

Adds substantial context beyond readOnlyHint/openWorldHint: the per-call result cap ('Up to 20 codes per call') and a concrete payment model ($0.002 USDC via x402 on Base, Solana or Arc, failed calls not charged). The cost/auth detail is exactly the kind of behavior annotations cannot express. Minor gap: no note on matching semantics (exact vs partial) or empty-result 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?

Three tight sentences, front-loaded with what the tool returns and immediately followed by scope exclusions, then limits and pricing. No filler or repetition.

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

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

For a two-parameter read-only lookup with an output schema, the description covers source, return contents, exclusions, result cap and billing. Only a note on match behavior and whether pricing applies per retry would make it fully self-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 100%, so both parameters are already documented with types and constraints; baseline 3 applies. The description's 'Up to 20 codes per call' merely restates the max parameter's range and adds nothing on term matching format.

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 and resource ('ICD-10-CM diagnosis code search'), names the upstream source (NLM Clinical Tables, CDC code set), and scopes the output to codes and official names. It does not explicitly route against siblings like health_cpt_hcpcs_procedure or health_loinc_laboratory_codes, but the code-system scoping makes the distinction inferable.

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 rather than stated: 'no cross-walks or clinical descriptions' sets a negative boundary, but the description never says when to pick this over a sibling such as health_cpt_hcpcs_procedure for procedures or health_mesh_biomedical_thesaurus for terminology lookup. An agent must infer the 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?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable context beyond annotations: it discloses a per-call cost ($0.002 in USDC), payment methods (x402 on Base, Solana, or Arc), and that failed calls are not charged. It also lists the returned fields, which helps the agent understand the output. Rate limits or latency are not mentioned, but the pricing detail is a significant addition.

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 long sentence but is front-loaded with purpose and filters, and every clause contributes useful information (scope, filters, return fields, pricing). Slightly dense, but no wasted words.

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

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

Given the presence of an output schema and annotations covering the safety profile, the description is complete enough. It adds essential pricing and payment details that are not in structured fields, and it indicates what data is returned. Minor gaps like rate limits or latency are not critical for this read-only facility 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 100%, so the input schema already documents all six parameters. The description lists the filters (state, IHS Area, city, name, service) but adds no meaning beyond what the schema provides, such as format examples or default behavior. Baseline 3 is appropriate when the schema does the heavy lifting.

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 it retrieves Indian Health Service, tribal and urban Indian health facilities from IHS's official map, with a specific list of filterable fields. It clearly distinguishes itself from sibling tools, which focus on other health data domains such as provider registries or clinical 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?

The description implies usage by listing available filters, but it does not specify when to use this tool versus alternatives (e.g., other health facility finders) or any exclusions. No explicit 'use when' or 'do not use when' guidance is 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 mark this as a read-only open-world lookup, and the description adds substantial behavioral context: pricing per successful call, x402 payment chains, and the fact that failed calls are not charged. It also discloses the flat-file KEGG REST source and a 100-gene cap, though it does not describe rate limits or failure modes.

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-loads what the tool returns before covering input, limits, and pricing. It is a dense paragraph rather than clearly structured sections, but every clause carries useful 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 an output schema present, the description need not explain return values, and it sufficiently covers source, input format, cap, and payment behavior. It is complete for calling the tool correctly, though it lacks sibling-usage 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?

Schema description coverage is 100%, so both the pathway number and max parameter are already documented in the schema, including the default of 20. The description reinforces the pathway-number format and the 100-gene maximum but adds little beyond the structured field documentation.

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 resource and verb: it retrieves KEGG human pathway details and the genes in that pathway, including which fields are returned. It is clear enough to distinguish from unrelated health tools, though it does not explicitly contrast itself with similar pathway or gene resources such as Reactome.

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 tells the agent the required input format (a five-digit human KEGG pathway number such as 05200) and the output cap, but it does not explain when to use this tool instead of a related pathway or gene tool. Usage is implied by the purpose rather than explicitly guided.

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 only declare readOnlyHint and openWorldHint, but the description adds material context beyond them: a $0.002 USDC per-successful-call x402 payment model across Base, Solana and Arc, the fact that failed calls are not charged, the 20-result cap, and the exclusion of units/reference ranges. It still does not disclose matching semantics (exact vs substring) 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 resource and operation are front-loaded before the payment details, and every clause carries information (scope, output shape, limits, pricing). It is dense but slightly long in a single sentence, though nothing is genuinely expendable given the pay-per-call model.

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 100% schema coverage and an output schema, the description needn't explain return values, and it still summarizes them (codes, names, total count). Payment terms and exclusions are covered; the only gap is how term matching behaves, which an agent may want before spending $0.002 per call.

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 both parameters are fully documented in the schema (max 1–20 default 10, term 2–60 characters). The description adds only the 'up to 20 per call' ceiling, which the schema already conveys, 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?

The description names the specific resource (LOINC laboratory and clinical test codes via NLM Clinical Tables) and the specific operation (match a term, return LOINC number and long common name plus total match count). No sibling tool covers LOINC, so the resource alone disambiguates it from ICD-10, CPT, or RxNorm siblings.

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: search LOINC names with a term, up to 20 results per call, and the definition warns that units and reference ranges are not included, which signals when to look elsewhere. However, it never states when to prefer this over a sibling terminology tool or what kind of term input works best.

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/openWorld, but the description adds real value beyond them: the results-pagination limitation, the exclusion of radiation safety data, and an explicit pricing model (per-successful-call, x402, failed calls free). It stops short of describing auth flow details but adds substantial operational context.

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?

A single front-loaded paragraph where the resource and scope come first, followed by limitations and pricing. Dense but most sentences carry information; the pricing sentence is lengthy but 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?

With an output schema present, the description need not explain return values, and it covers the key gaps: page-limit truncation, excluded radiation data, and cost. Adequate for an agent to decide and call correctly, though no explicit alternative routing is given.

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 both parameters (state two-letter code, max 1-50) are fully documented in the schema. The description adds no syntax or semantic detail beyond what the schema already provides; 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+resource (FDA MQSA certified mammography facilities), scopes it to one US state, and enumerates the returned fields (name, phone, city, ZIP, facility ID). This clearly distinguishes it from the dozens of other health registry siblings.

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 state-level scoping implies when the tool applies, but nothing says when to prefer it over siblings or when it is inappropriate. The 'first results page only' note functions as a latent usage constraint rather than explicit guidance.

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 the read-only and open-world profile, but the description adds genuinely non-structured context: the source vintage (newest Star Ratings Data Tables), the rating scale including half stars, and the payment model ($0.002 USDC via x402 on Base/Solana/Arc) with the important guarantee that failed calls are not charged. Cost and billing surface are exactly the kind of traits annotations cannot express.

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 resource and source, then filters, then pricing. Efficient overall, though the field enumeration partly duplicates the output schema and the pricing sentence is run-on with three payment rails packed together.

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 annotations, full schema coverage and an output schema, the description only needs to add provenance and cost, which it does. Minor gaps: no mention that limit/offset are strings or of paging behavior in prose, and 'newest' does not name a specific rating year, leaving the agent to infer vintage.

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% with per-parameter examples in the schema (e.g. 'H0028', 'Humana', 'Local CCP, PDP, PFFS'), so the schema carries parameter meaning fully. The description's 'search by contract ID, organization or parent name, organization type or minimum overall stars' merely restates the filter names and adds no syntax or matching-behavior detail beyond what is already documented.

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 resource (official CMS Medicare Star Ratings for Medicare Advantage Part C and Part D contracts) from a named source (newest Star Ratings Data Tables) and enumerates the exact fields returned. An agent can distinguish it from health_cms_medicare_part_d or health_hospitallink_cms_ratings without opening the schema.

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?

Explains the available search axes (contract ID, organization or parent name, organization type, minimum overall stars), which gives clear context for how to query. It does not, however, explicitly route the agent away from related sibling datasets such as health_cms_medicare_part_d when the task requires claims-level Part D data.

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/openWorldHint annotations, it discloses pricing ($0.002 USDC per successful call), the payment rails (x402 on Base, Solana or Arc), that failed calls are not charged, and the hard 20-row cap. Those are exactly the operational facts an agent needs before deciding to spend money on a call.

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?

Purpose is front-loaded in the first clause and the second sentence cleanly carries cost/limit information. The mid-sentence enumeration of return fields (hospital name, state, DRG code, discharges, average charges and payments) is partly wasted since an output schema already exists.

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?

Everything needed to call correctly is present: dataset provenance, the unit of analysis (hospital-level averages, not national rates), filtering semantics, row ceiling, and cost/payment mechanics. Return shape is covered by the output schema, so its omission from the description is not a gap.

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 drg (3-digit code, example 871), state, and max (1–20, default 5). The description restates the same semantics without adding format or edge-case guidance, so the baseline of 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?

The description states a specific verb+resource (CMS Medicare inpatient hospital averages per MS-DRG), names the data source (data.cms.gov, fee-for-service Part A), and explicitly excludes the adjacent IPPS national rate table. An agent can tell this is hospital-level DRG cost data rather than a national rate 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?

It gives clear invocation context: filter by 3-digit DRG code, optionally narrow by state, results capped at 20 rows. It draws a scope boundary against the national rate table, though it never routes the agent to a specific sibling tool among the many health_* tools (e.g. hospitallink_cms_ratings or physician_compare_cms).

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 openWorldHint=true. The description adds meaningful behavioral context beyond them: result cap, pricing of $0.002 USDC per successful call, x402 payment networks, and that failed calls are not charged; it does not cover rate limits or other operational details.

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

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

The description is front-loaded with the core purpose and constraints, and the pricing sentence is useful. Some return-field detail overlaps with the output schema, but overall it remains dense and purposeful rather than padded.

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 four parameters, full schema coverage, an output schema, and read-only/open-world annotations, the description supplies the remaining context an agent needs: coordinate-only input, result cap, cost, and failure-charge policy. No essential invocation or selection information is 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 description coverage is 100%, so the schema already documents lat, lng, max, and radiusMiles with ranges and defaults. The description reinforces the coordinate-only input model and the 20-result cap, but adds little about radiusMiles or formatting beyond what the schema provides.

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 resource and action: SAMHSA FindTreatment facilities near a latitude/longitude, including the fields returned. It clearly distinguishes the scope as a geo-based treatment-facility locator, though it does not explicitly contrast itself with any sibling 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?

It gives the key usage constraint — provide lat/lng, not ZIP or city — and states a 20-facility cap. However, it does not name alternative tools or explicitly say when this locator is preferable to other health lookup siblings, so usage is mostly implied by the description.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the payment model (x402, USDC, Base/Solana/Arc), the exact price per successful call, and that failed calls are free — critical cost behavior for an agent deciding whether to invoke. Also discloses an output limitation (scope notes absent) that 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?

Three dense, front-loaded sentences: what it returns, the exact-match limitation, then cost. No filler, and the most decision-relevant constraint (exact match) precedes the pricing 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?

An output schema exists, so return-shape gaps are covered, and the description still names the returned fields. Payment, failure-charging, and the exact-match requirement give an agent everything needed to call it correctly without probing.

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% and the single 'heading' parameter is fully documented with charset and length constraints, so the schema carries the parameter burden. The description only reinforces the exact-match requirement, which is useful but adds little beyond the schema baseline.

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?

Names a specific source (NLM MeSH), a specific resource (one descriptor for an exact heading), and enumerates exactly what is returned (ID, label, entry terms, allowable qualifiers). No sibling tool covers MeSH, and the scope is unambiguous from the first clause.

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

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

Explicitly states the operative constraint ('Exact match only') and one exclusion ('no scope notes, the public lookup API does not return them'), so an agent knows a partial/fuzzy heading will fail. It stops short of suggesting an alternative for non-exact lookups, which keeps it below 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?

Annotations already declare readOnlyHint and openWorldHint, but the description adds genuinely useful behavior: pricing of $0.002 USDC per successful call via x402 on Base/Solana/Arc, and that failed calls are not charged. That payment/settlement detail is exactly the kind of context annotations cannot convey. It stops short of describing pagination beyond the 20-per-call cap.

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 dense sentences: purpose and returned fields first, then limits and pricing. Front-loaded and essentially waste-free, though the pricing clause is slightly crammed into the same sentence as result semantics.

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, return values needn't be explained, and the description covers scope, cap, ordering, and cost/payment model. The only gap is that x402 implies wallet/auth prerequisites that aren't spelled out, which matters for a paid open-world read.

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%, with both q (2-100 chars) and max (1-20, default 5) fully documented in the schema. The description reinforces the 'up to 20' cap and adds ordering ('most relevant first'), but adds little syntax or format beyond what the schema already provides, so the baseline of 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?

The description gives a specific verb and resource ('NIH RePORTER funded research projects matching a text search') and enumerates the returned fields (project number, title, fiscal year, award amount, lead organization, PIs). It's clearly distinguishable from siblings like health_pubmed_abstracts or health_clinical_trials_gov, though it doesn't explicitly name which sibling to prefer when both could serve.

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 implies usage via 'matching a text search' and states result limits and pricing, but offers no explicit when/when-not guidance or alternative routing against the dozens of health siblings. An agent has to infer that this is the grant-award lookup rather than publications or trials.

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 and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond them: the 10-record cap per call, the exact cost ($0.002 USDC via x402 across Base/Solana/Arc), and that failed calls are not charged — material for an agent deciding to invoke a paid tool.

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 compact sentences with zero filler: scope first, then match semantics, then the cap and price. Every sentence carries information the agent needs and nothing is buried.

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?

Output schema exists so return values need no explanation, annotations cover the safety profile, schema covers parameters, and the description fills the remaining gaps an agent needs — result cap, fuzziness caveat, and paid-call economics with failure exemption.

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 all four parameters (last_name, first_name, state, max) are already fully documented in the schema. The description adds nothing parameter-level, which is the expected baseline when the schema does the heavy lifting.

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 ('search') against a named authoritative source (CMS NPPES NPI Registry) and enumerates the returned fields (NPI, name, credential, status, taxonomy, practice location). An agent can distinguish this from physician_compare_cms or state_medical_board tools by the NPPES source, though it never explicitly contrasts itself with those siblings.

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 mention that 'matches can be fuzzy; the registry decides the match' implies a name-based lookup context, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many physician/medical-board siblings. Usage is inferable rather than stated.

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