Server Quality Checklist

Tool Scores

• get_medication_listA
  4/5.0
  Behavior4/5

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

  Beyond annotations indicating read-only, the description adds behavioral details: results are grouped by category, each entry includes fields like id and schedule, filtering is optional, and it is available on the FREE tier. No safety concerns disclosed.

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

  Conciseness5/5

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

  The description is three sentences, each adding value: purpose, output format, and optional filter with FREE tier. No wasted words; front-loaded with the main action.

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

  Completeness4/5

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

  For a list tool with simple parameters and many siblings, the description covers the essential aspects: what is returned, filtering, and the fact that the id is used by other tools. Could benefit from mentioning if pagination exists, but not critical.

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

  Parameters3/5

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

  The schema covers 100% of parameters with clear descriptions. The description repeats the filtering option without adding new meaning beyond what the schema already provides, so baseline 3.

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

  Purpose5/5

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

  The description clearly states it returns the full catalog of medications grouped by category, with specific fields included. It distinguishes from sibling tools by focusing on list retrieval, while others handle details, FDA status, etc.

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

  Usage Guidelines3/5

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

  Usage is implied by the description (filtering by category), but no explicit guidance on when to use this tool versus alternatives like get_medication_details. No when-not or exclusions mentioned.

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

• check_contraindicationsA
  4.1/5.0
  Behavior4/5

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

  The description is consistent with the readOnlyHint annotation, indicating a non-destructive screening operation. It adds behavioral context by detailing the output format (verdict and findings) and noting the PREMIUM tier, which implies access or cost considerations. No contradictions 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.

  Conciseness4/5

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

  The description is a single sentence that conveys all essential information efficiently. It is front-loaded with the key purpose and output. While concise, it could be slightly streamlined, but overall it is well-structured.

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

  Completeness4/5

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

  For a tool with 5 parameters and no output schema, the description adequately explains the return values (verdict, triggering findings, clinical notes). It also implies the need for patient profile data. However, it lacks details on error handling or edge cases, which would improve completeness.

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

  Parameters4/5

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

  All 5 parameters have descriptions in the schema (100% coverage). The description adds semantic value by explaining how these parameters are used (screening against absolute/relative contraindications and drug interactions), which goes beyond the schema's basic definitions.

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

  Purpose5/5

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

  The description clearly states the tool's function: given a medication and patient profile, it screens for contraindications and interactions, returning a verdict (PASS, FLAG, REJECT) with specific findings and clinical notes. This distinguishes it from siblings like get_medication_details or check_drug_interactions.

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

  Usage Guidelines3/5

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

  The description mentions 'PREMIUM tier' but does not explicitly specify when to use this tool versus alternatives such as check_drug_interactions. No guidance on exclusions or prerequisites is provided, leaving the agent to infer usage context.

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

• get_fda_statusA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true. The description adds value by enumerating the returned data (approval status, schedule, pathway, uses, off-label note), giving the agent a clear picture of output beyond the schema.

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

  Conciseness5/5

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

  Two sentences cover input, output, and importance. No extraneous details; each word serves a purpose. Properly front-loaded for quick consumption.

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

  Completeness4/5

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

  For a single-parameter tool with no output schema, the description lists all major output categories. 'Reference pointers' is slightly vague, but overall it provides enough context for appropriate use among siblings.

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

  Parameters3/5

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

  Schema coverage is 100% with a clear parameter description. The description reinforces the acceptable input types (name, id, brand/alias) but adds little beyond what the schema already provides.

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

  Purpose5/5

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

  The description specifies the action: given a compound identifier, returns FDA status, DEA schedule, compounding pathway, and other regulatory info. It clearly distinguishes from siblings like get_medication_list or get_dosing_protocol by focusing on regulatory/compliance data.

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

  Usage Guidelines4/5

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

  The phrase 'Essential for compliant compounded-medication practice' clearly indicates when to use (for regulatory compliance). While it doesn't explicitly exclude other tools, the sibling names and unique purpose provide sufficient context.

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

• get_medication_detailsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the description's addition of return fields and 'FREE tier' provides useful behavioral context beyond the annotation. No contradictions. Could mention any rate limits or response size, but not necessary for a simple query.

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

  Conciseness5/5

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

  Two sentences with no wasted words. The first sentence lists all return fields in a clear, scannable format, and the second adds the 'FREE tier' note. Perfectly concise and front-loaded.

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

  Completeness4/5

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

  For a single-parameter tool with no output schema, the description adequately covers the return values (drug class, MOA, formulations, etc.). It mentions 'at-a-glance cautions' to set expectations. Could be improved by noting the response structure or whether results are paginated, but not critical.

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

  Parameters4/5

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

  Schema description covers the parameter (100% coverage), but the tool description adds examples (e.g., 'tirzepatide', 'Ozempic') and clarifies that the input can be a name, id, or alias, which enhances understanding beyond the schema.

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

  Purpose5/5

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

  Description clearly states the verb 'returns' and specifies the resource: drug class, mechanism of action, formulations, candidate profile, cautions, and schedule. This distinguishes it from sibling tools like get_medication_list (list) or get_dosing_protocol (specific aspect).

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

  Usage Guidelines3/5

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

  The description implies the tool should be used when comprehensive medication details are needed, but it does not explicitly state when not to use it or mention alternative sibling tools for specific aspects (e.g., check_contraindications for deeper contraindications).

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

• get_required_labsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the agent knows it's a safe read. The description adds value by describing the output structure (grouped panels with clinical rationale) and noting the PREMIUM tier, which implies access limitations. 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.

  Conciseness5/5

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

  The three-sentence description is front-loaded with the core function, then usage context, then tier. Every sentence adds value with no fluff, making it highly efficient for an AI agent.

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

  Completeness4/5

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

  For a simple tool with one parameter and read-only annotations, the description covers the key aspects: what it returns (baseline labs grouped with rationale), when to use (pre-treatment workup), and tier. It could be improved by specifying the expected output format more explicitly, but it's largely complete without an output schema.

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

  Parameters3/5

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

  The single parameter 'medication' is fully described in the schema (name, id, or alias) with 100% coverage. The description adds no new semantic details about the parameter beyond the schema, so a baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool returns recommended baseline labs/assessments to obtain before prescribing a medication, grouped into panels with clinical rationale. This verb+resource combination is specific and distinguishes it from siblings like get_monitoring_plan (ongoing monitoring) and check_contraindications.

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

  Usage Guidelines4/5

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

  The description explicitly says 'Use to build a pre-treatment workup' and emphasizes 'BEFORE prescribing', providing clear context for when to use. However, it does not explicitly state when not to use it or point to alternatives, though the sibling list and phrasing imply differentiation from post-prescription tools.

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

• screen_patient_intakeA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, but description adds behavioral context: the output includes first-line/adjunct medications, workup, and things to avoid. This goes beyond what annotations provide, giving a clear picture of the tool's results and non-destructive nature.

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

  Conciseness5/5

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

  Two sentences with no wasted words. First sentence defines purpose and provides an illustrative example. Second sentence provides usage directive and tier. Front-loaded with key information.

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

  Completeness4/5

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

  Given no output schema, the description adequately explains the return value (pathways with medications, workup, avoid list). Both input parameters are covered, and the tool's role in triage is clear. Missing details like pagination or limit but acceptable for a screening tool.

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

  Parameters3/5

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

  Schema coverage is 100% and schema descriptions are clear. Description adds an example ('fatigue, low libido, want to lose weight') and notes combination behavior, providing marginal extra value beyond the schema.

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

  Purpose5/5

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

  Description clearly states the tool's purpose: given symptoms/goals, suggests longevity treatment pathways. It distinguishes from sibling tools which focus on specific medication details, FDA status, dosing, etc. The verb 'suggests' and resource 'treatment pathways' are specific and unambiguous.

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

  Usage Guidelines4/5

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

  Explicitly says 'Use to triage an intake' and mentions it is PREMIUM tier, which indicates when to use. Lacks explicit exclusions or alternatives, but the context of siblings (e.g., get_medication_list) implies this is the initial screening step, not a detail lookup.

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

• get_monitoring_planA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the agent knows it's a safe read. The description adds the 'PREMIUM tier' label, which indicates access or rate limit considerations. No contradictions 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.

  Conciseness5/5

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

  Two sentences, front-loaded with core purpose, followed by usage hint and tier. Every sentence adds value with no redundancy. Efficient and clear.

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

  Completeness5/5

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

  For a simple tool with one parameter and no output schema, the description fully covers purpose, usage context, and a behavioral note (tier). It is complete enough for an agent to select and invoke correctly.

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

  Parameters3/5

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

  The schema has 100% description coverage for the single parameter ('medication'), so the schema already explains what it accepts. The tool description's phrase 'Given a medication' adds no new 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.

  Purpose5/5

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

  The description clearly states the verb ('returns') and the resource ('ongoing monitoring requirements'), specifying the context ('once therapy has started') and what it includes ('what to check, at what interval, threshold'). This distinguishes it from sibling tools like get_required_labs, which likely cover pre-therapy labs.

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

  Usage Guidelines4/5

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

  The description explicitly states the use case ('build a follow-up schedule') and implies when to use (after therapy starts). It does not explicitly say when not to use or name alternatives, but the sibling context and the phrase 'once therapy has started' provide implicit differentiation.

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

• check_drug_interactionsA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate read-only (readOnlyHint=true). Description adds output details (severity ranking, mechanism, management) 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.

  Conciseness5/5

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

  Two sentences, front-loaded with key purpose, no unnecessary words.

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

  Completeness4/5

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

  For a tool with one parameter and no output schema, the description adequately explains input and output structure. Could hint at what 'management' includes but is sufficient.

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

  Parameters4/5

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

  Schema covers 100% of parameters with good descriptions. The description adds context about accepting both catalog drugs and outside agents, enhancing usability.

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

  Purpose5/5

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

  The description clearly states the verb ('returns'), resource ('pairwise interaction warnings'), and distinguishes from siblings like 'check_contraindications' by specifying severity ranking and input flexibility.

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

  Usage Guidelines4/5

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

  The description says when to use ('given a list of medications'), but does not explicitly exclude alternatives like 'check_contraindications'. However, the context implies this is for general interaction checks.

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

• get_dosing_protocolA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so no contradiction. Description adds value by listing the specific outputs (route, starting dose, etc.), providing transparency beyond the annotation.

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

  Conciseness5/5

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

  Very concise: three sentences front-load the purpose and key outputs. No fluff, every sentence adds value.

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

  Completeness5/5

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

  Despite no output schema, description fully explains return values (list of fields) and behavior with/without indication. Sufficient for a simple read tool with two parameters.

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

  Parameters4/5

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

  Schema coverage is 100% with clear parameter descriptions. Description reinforces the optional nature of indication and explains the different behavior (best-matching vs all indications), adding meaning.

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

  Purpose5/5

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

  Description clearly states the tool returns evidence-based dosing for a medication, listing specific output fields like route, dose, etc. It distinguishes from siblings such as get_medication_list or get_medication_details by focusing solely on dosing protocols.

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

  Usage Guidelines4/5

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

  Description explains when to use the indication parameter versus not, but does not explicitly compare to alternative tools. However, sibling names are distinct enough that the tool's purpose is clear.

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