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

Annotations already convey readOnlyHint and openWorldHint, so the safety profile is covered. The description adds meaningful behavioral boundaries: it is educational, does not compute a risk score, and does not recommend urgency—all beyond what annotations provide. No contradiction with 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?

Two short sentences with no filler. The core function is front-loaded, and the critical limitation is stated immediately after, making the description highly scannable and easy to parse.

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-only tool, the description covers purpose, input, and a key behavioral limitation. It does not describe the return format, but no output schema exists and the verb 'describe' implies descriptive text. Overall it is complete enough for an agent to invoke correctly, with a minor 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%: the riskFactorIds parameter is fully documented with an example array. The description only refers generically to 'a list of factor IDs' and adds no new parameter-level detail, 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 uses a specific verb ('describe') and resource ('named educational skin-health factors'), and explicitly states what it does not do ('does not calculate a risk score or recommend urgency'). This clearly distinguishes it from sibling tools like get_user_risk_factors or classify_lesion_features, which imply different operations.

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

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

The description makes usage context clear: use when you have factor IDs and need educational descriptions of those factors. It explicitly excludes risk scoring and urgency assessment, serving as a when-not condition. However, it does not name an alternative tool for those cases, so the guidance is strong but not fully explicit.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description's educational-only framing adds context beyond the annotations. It explicitly discloses that the tool does not provide diagnostic conclusions, risk levels, or urgency recommendations, which is valuable behavioral context for an agent deciding whether to use this tool in a clinical scenario. The description does not contradict 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?

Two sentences with no wasted words. The core purpose is stated first, followed by a clear boundary of what the tool does not do. Every sentence earns its place.

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

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

For a read-only, educational tool with 5 optional parameters and no output schema, the description is largely complete. It clarifies the educational scope and non-diagnostic nature, which is the most important contextual information. It could mention that all parameters are optional, but the schema already shows required: [], so the description need not repeat that. The lack of output schema means the agent won't know the return format, but for an educational description tool this is a minor 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 all 5 parameters clearly. The description adds the overall context that these parameters are ABCDE criteria, but it does not add per-parameter meaning beyond what the schema provides. Baseline 3 is appropriate since 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 states a specific verb ('Describe') and resource ('ABCDE criteria supplied for a lesion'), and clarifies it is educational only. It distinguishes itself from risk assessment tools by explicitly saying it does not name a condition, assign risk, or recommend urgency, which helps differentiate it from siblings like assess_risk_from_factors and get_mole_analysis.

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

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

The description clearly indicates when to use this tool: when describing ABCDE criteria for a lesion in an educational context. It also provides exclusions by stating what it does NOT do (name a condition, assign risk, recommend urgency), which implicitly tells the agent not to use it for diagnosis or risk assessment. However, it does not explicitly name alternative tools for those purposes.

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, covering safety and open-world assumptions. The description adds valuable behavioral context by stating 'Reports observed differences only — not a diagnosis', clarifying that the output is limited to observed differences and does not provide medical judgment. This goes beyond the annotations and sets proper expectations for the agent.

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

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

The description is two sentences with no redundancy. It front-loads the action ('Compare two recorded mole photos') and immediately adds the key limitation ('not a diagnosis'). Every word earns its place, making it highly efficient.

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

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

The tool is relatively simple, and the schema covers all parameters. However, since there is no output schema, the description only vaguely mentions 'Reports observed differences' without specifying the output format (e.g., list of changes, textual summary). It also does not differentiate from the sibling get_mole_changes, which could lead to ambiguous tool selection. While the core purpose is clear, these gaps prevent a higher score.

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 each parameter already has a clear description (e.g., imageId1 'First image ID (older)', imageId2 'Second image ID (newer)'). The tool description adds no additional parameter semantics, so the baseline score 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 clearly states the tool's function: 'Compare two recorded mole photos' – a specific verb and resource. It also distinguishes itself from diagnostic tools by noting 'not a diagnosis', which differentiates it from siblings like classify_lesion_features or assess_risk_from_factors. This makes the tool's purpose unambiguous.

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

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

The description implies the usage context (comparing two photos of a mole) but does not explicitly mention when to use this tool versus alternatives like get_mole_changes, which might also track differences over time. There is no mention of exclusions or alternative routing, leaving the agent to infer the appropriate scenario.

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 readOnlyHint/openWorldHint annotations already cover safety and open-world behavior. The description adds that paths are 'potential' and gives an example, which is useful but does not disclose return format, limitations, or how incomplete matches are handled.

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

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

Two short sentences, front-loaded with the primary action, and an illustrative example. No filler or redundant restatement of the tool name.

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

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

For a single-parameter, read-only lookup, the description gives enough context: it states the input purpose, the kind of output (potential progression paths), and an example. It doesn't specify pagination or formatting, but that's not necessary for this simple 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% since the only parameter, snomedCode, is described. The description does little beyond confirming the condition is identified by a SNOMED CT code, so it mostly relies on 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 uses a specific verb and resource ('Get information about how a skin condition can progress') and gives a concrete example ('dysplastic nevus to melanoma'). This clearly differentiates it from sibling tools like get_condition_risk_factors by focusing on progression paths.

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

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

The description provides no guidance on when to use this tool versus alternatives such as lookup_medical_concept, get_condition_risk_factors, or search_medical_info. No selection criteria or exclusions are given.

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 value by giving examples of the returned factors (family history, skin type, UV exposure), which informs the agent about the nature of the output without contradicting 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 sentence that is front-loaded with the action and resource, followed by examples. 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?

For a simple read-only lookup with one parameter and no output schema, the description provides sufficient information about what is returned (a list of risk factors with examples). The openWorldHint annotation covers non-exhaustiveness, and the tool is simple enough that no further details are needed.

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

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

The input schema fully describes the single parameter snomedCode with a description. The tool description does not add additional semantic detail beyond that, so the baseline of 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 clearly states the verb 'Get' and the resource 'risk factors associated with a specific condition', and specifies that it takes a condition code. This distinguishes it from sibling tools like get_user_risk_factors which focus on a user's risk profile rather than a condition.

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

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

The description implies usage for a specific condition via SNOMED code, but does not explicitly name alternatives or exclusions. However, the context is clear enough that an agent would know to use this when they have a condition code and need its risk factors, as opposed to user-specific 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 declare readOnlyHint=true and openWorldHint=true, so the description only needs to add behavioral context. It adds ontology-wide scope, but does not describe list contents, pagination, or any caveats about the returned data. This is adequate but not rich.

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

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

Two short sentences, front-loaded with the core operation. The second sentence is slightly redundant by restating 'malignant skin conditions' as 'skin cancers,' so it is concise but not 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 parameterless read-only list tool, the description states what it returns and its purpose, and the lack of an output schema is mitigated by the simple list semantics. It could be slightly more complete by noting what fields or format the returned list contains.

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

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

The tool has zero parameters, so the input schema is fully documentative and no parameter explanations are needed. The description appropriately adds no parameter-specific details; the parameterless baseline of 4 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 identifies a specific verb ('Get'), resource ('list of all malignant skin conditions'), and scope ('in the ontology'). It is distinguishable from sibling concept-search tools by emphasizing 'all malignant skin conditions,' though it does not explicitly name a sibling it is not.

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 advises 'Use for educational purposes about skin cancers,' which gives an intended context but no when-not-to-use guidance and no comparison with alternatives such as lookup_medical_concept or search_medical_concepts. The usage guidance is present but not robust.

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

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

The description adds the valuable context that data is 'recorded' and that output is for educational purposes only. Annotations already provide readOnlyHint=true, so the safety profile is covered. It does not describe return format or pagination, but that is less critical for a simple one-parameter getter.

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 operation and resource, and includes the critical educational caveat immediately. No filler or redundancy.

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

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

Given the single parameter and read-only nature, the description sufficiently frames what the tool returns and its limitations. A brief note on output format would be a minor improvement, but nothing essential is missing for an agent to select and invoke it.

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

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

The schema fully documents moleId as 'The mole's unique identifier' with 100% coverage. The description adds no extra parameter guidance, so it provides no value beyond the structured 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 uses a clear verb ('Return') and specifies the resource ('recorded ABCDE feature measurements for a mole'). The 'not a diagnosis or risk level' caveat helps separate it from risk-focused siblings like get_user_risk_factors, though it doesn't explicitly name alternatives.

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

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

The description implies when to use the tool—when recorded ABCDE measurements are needed—and adds a clear boundary with 'Educational only — not a diagnosis or risk level.' However, it does not explicitly reference sibling tools or contrast cases (e.g., when to use get_mole_changes instead).

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

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

Annotations already declare readOnlyHint=true, so the safety profile is clear. The description adds useful context that the output consists of observations rather than a verdict, but does not disclose additional behavioral details such as ordering, absence of results, or output structure.

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

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

Two short sentences with no filler. The core action and scope are front-loaded, and the exclusion of trend verdicts is stated immediately after, which is economical and effective.

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

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

For a one-parameter read-only tool with no output schema, the description adequately conveys what the tool returns and what it does not. It could mention output format or behavior on missing history, but the low complexity means nothing essential 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%, and the schema already documents moleId as 'The mole's unique identifier.' The description only references 'a mole' generically and adds no parameter-level meaning beyond the schema.

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

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

The description uses a specific verb and resource: 'Return recorded appearance changes for a mole over time.' The qualifier 'Observations only — not a trend verdict' clearly distinguishes it from analysis-oriented siblings like get_mole_analysis or get_condition_progression.

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

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

The description gives clear context: use this tool when you need raw recorded appearance changes over time, not an interpretive trend verdict. It implies but does not explicitly name an alternative for trend analysis, so it falls just short of full 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. The description adds a useful behavioral boundary: this is educational record data, not a risk ranking. It does not disclose details like pagination or image-date formatting, but for a simple read-only listing the key behavior is conveyed.

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

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

Two short, information-dense sentences with no filler. The main action and resource are front-loaded, and the important 'educational only' caveat is placed at the end without bloating the 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?

For a single-parameter read-only listing with no output schema, the description covers the core purpose and the important caveat. It could have briefly mentioned output ordering, pagination, or what 'last photo dates' means, but the essential information an agent needs to invoke it correctly is present.

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%: userId is documented with type, pattern, maxLength, and description. The description's 'a user's' maps naturally to userId, but it adds no additional meaning beyond what the schema already 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 names a specific verb ('List') and a specific resource ('a user's recorded moles and last photo dates'). Adding 'Educational records only — not a risk ranking' distinguishes it from risk-oriented siblings like get_user_risk_factors and assess_risk_from_factors.

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

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

The description clearly states what this tool is not for ('not a risk ranking'), which helps an agent avoid using it for risk assessment. However, it does not explicitly name alternative tools or state when to prefer them over this one.

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 read-only and open-world behavior. The description adds meaningful context beyond that: the output is a list of named educational factorsasi and that no risk score is computed. This clarifies the tool's operational scope without contradicting the annotations.

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

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

Single sentence with the core operation first and a key exclusion second. No filler or repetition of schema details.

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

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

For a simple one-parameter read-only list operation, the description is sufficient: it names the resource, the user scope, and the non-scoring behavior. It could be slightly more specific about the output shape, but the low complexity and explicit 'List ... factors' make this a minor 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 coverage is complete for userId, including pattern and required status. The description only adds that the resource is user-specific, which is mild additional context. Baseline 3 is appropriate because the schema already carries the parameter semantics.

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

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

The description uses a specific verb ('List') and resource ('named educational skin-health factors on a user profile'), and explicitly disambiguates from scoring tools by saying it does not calculate a risk score. This clearly distinguishes it from siblings like assess_risk_from_factors and get_condition_risk_factors.

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

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

The description gives clear context: this tool lists factors rather than scoring them axes. The negative clause 'Does not calculate a risk score' signals when this tool is NOT appropriate. It does not explicitly name alternative siblings, but the exclusion is concrete enough for an agent to route correctly.

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

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

Annotations already declare readOnlyHint=true, so the description doesn't need to state that it's read-only. It adds the scope (skin conditions) and content (severity, category), but does not disclose potential limitations (e.g., only handles skin codes, behavior on invalid codes) or the return structure. It does not contradict annotations.

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

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

The description is two sentences, front-loaded with the primary action and scope, followed by a brief usage note. Every word adds value, with no redundancy or filler. It is highly efficient and easy to scan.

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

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

With no output schema, the description must convey what the tool returns. It mentions 'detailed information about skin conditions including severity and category,' which gives a high-level view but lacks specifics like exact fields, formatting, or error handling. The scope (skin conditions) is stated but not justified, and no guidance is given for invalid codes or edge cases. The description is adequate but leaves room for ambiguity.

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

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

The schema provides full documentation for snomedCode with an example, achieving 100% coverage. The description adds no extra detail about the parameter format, validation, or acceptable code ranges, so it relies on the schema. Baseline 3 is appropriate given complete schema coverage.

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

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

The description clearly states the action (look up), the resource (medical concept), and the key identifier (SNOMED CT code). It also specifies the domain (skin conditions) and the output content (severity, category), which distinguishes it from siblings like search_medical_concepts (text search) and map_snomed_to_icd10 (code mapping). The purpose is unambiguous.

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

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

The description provides a usage context ('Use this to provide accurate medical terminology') but does not explicitly state when not to use it or how it compares to alternatives like search_medical_concepts or get_condition_risk_factors. It implies a read-only informational lookup but lacks exclusions or selection criteria.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, which cover the read-only nature and potential incompleteness of mappings. The description adds only a minor note about 'official' classifications, which does not meaningfully extend behavioral context. It is consistent with the annotations but does not disclose additional behaviors such as output format or edge cases.

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

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

The description is two short sentences with zero filler. The core action and target are front-loaded in the first sentence, and the second sentence adds a brief use case. Every word earns its place.

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

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

Given the simplicity (one required parameter, no output schema, and annotations covering read-only and open-world behavior), the description is mostly sufficient. It explains the primary function and a typical use case. However, it does not describe the return format or note that some SNOMED codes may not map, though these are minor given the tool's straightforward nature.

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

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

The schema description for 'snomedCode' ('SNOMED CT code to map') is complete, covering 100% of the parameter. The tool description adds no extra information about the parameter 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 clearly states a specific verb ('Map') and resource ('SNOMED CT code to ICD-10 diagnosis codes'). This is unambiguous and distinct from sibling tools like lookup_medical_concept or search_medical_concepts, which focus on retrieving concepts rather than cross-coding. The purpose is immediately clear.

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

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

The description provides a mild usage hint ('Useful for understanding official diagnosis classifications') but does not explicitly state when to use this tool over alternatives, nor does it name any sibling tools. Usage context is implied but not clearly delineated, leaving the agent to infer when mapping is appropriate.

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, covering safety and non-exhaustiveness. The description adds that results are SNOMED CT concepts specifically for dermatology, and that search matches by name or description—useful context beyond the annotations. No contradiction.

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

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

Two sentences with zero filler. The core action and scope are front-loaded, and every clause adds information. Ideal length for a tool with a single parameter.

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

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

For a simple one-parameter search tool, the description covers the return format (SNOMED CT concepts) and domain (dermatology). It lacks details on result limits or pagination, but given the openWorldHint and simplicity, this is a minor gap. The absence of an output schema is partially mitigated by the description's high-level return type.

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 query parameter is already well described with examples. The description adds the semantic detail that the search can match by both name and description, which is not present in the schema. This enriches the parameter understanding.

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 ('Search') and resource ('medical concepts'), and narrows the scope to SNOMED CT and dermatology. This clearly differentiates it from sibling tools like get_user_moles (personal data), map_snomed_to_icd10 (mapping), and lookup_medical_concept (exact lookup).

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

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

The description implies a free-text search use case but does not explicitly contrast it with alternatives such as lookup_medical_concept (exact ID) or search_medical_info (broader scope). Given the abundance of sibling tools, explicit guidance on when to prefer this tool over others would be valuable, but its basic purpose is clear.

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

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

Annotations already communicate read-only intent. The description adds minimal behavioral context beyond the subject matter — it doesn't mention result formats, ordering, or limits. No contradiction.

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

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

Two short sentences, front-loaded with action and domain, examples included. No dead weight.

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?

This is a simple read-only search with one well-described parameter and no output schema; the description states intended use (educational content for skin conditions) and scope, which is sufficient for an agent to pick it correctly. Slight ambiguity vs 'search_medical_concepts' but the skin-health qualifier resolves it.

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 covers the only parameter with a description and examples (100% coverage). The description adds no additional parameter 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 uses a specific verb ('Search') and clearly identifies the resource (medical knowledge base for skin health information) with concrete examples (ABCDE criteria, prevention tips). The 'skin health' scope helps distinguish it from the sibling search_medical_concepts, though it does not explicitly name competitors.

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?

States a clear use case: to provide accurate educational content about skin conditions and related criteria. It doesn't explicitly state when to use search_medical_concepts or other alternatives, but the skin-specific context makes the intended use evident.

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