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

With no annotations provided, the description carries full burden. It discloses '[Premium]' access restriction and that it 'Returns known private tag meaning', indicating read-only behavior. However, it lacks details on error handling (unknown tags/vendors), return format structure, 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?

Two sentences with zero waste. Front-loaded with access tier '[Premium]', followed by action 'Decode', scope 'vendor-specific private DICOM tags', and return value description. 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?

For a 2-parameter tool with 100% schema coverage and no output schema, the description adequately covers the basic operation but lacks specifics on return format, error states, or fallback behavior when tags are unknown. Minimum viable for the complexity level.

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%, establishing baseline 3. The description reinforces the vendor parameter by listing supported vendors (Philips, GE, etc.), but does not add syntax details, validation rules, or semantic relationships 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 uses specific verb 'Decode' with resource 'vendor-specific private DICOM tags' and explicitly lists supported vendors (Philips, GE, Siemens, etc.). It clearly distinguishes from siblings like lookup_dicom_tag and explain_dicom_tag by specifying 'private' tags versus standard DICOM tags.

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

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

Provides clear context by specifying this handles 'private' DICOM tags from specific vendors, implicitly guiding selection when standard tag lookups fail. However, it does not explicitly name sibling alternatives (e.g., 'use lookup_dicom_tag for standard tags') or state exclusion 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?

With no annotations provided, the description carries the full burden and succeeds by disclosing specific content domains: vendor-specific quirks (Philips, GE, Siemens), common values, related tags, and gotchas. This gives the agent clear expectations about the explanation's scope and depth.

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

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

Single, dense sentence that is appropriately front-loaded with the core action. Every clause (vendor quirks, gotchas, related tags) earns its place by differentiating the tool's output. Slightly information-dense but efficient for the complexity described.

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 lookup tool with no output schema, the description adequately compensates by qualitatively describing the detailed explanation content. It appropriately focuses on what the explanation contains rather than structural return values.

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% ('DICOM tag identifier (number or keyword)'), establishing a baseline of 3. The description references the tag implicitly but does not add syntax examples, format specifications, or validation rules 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?

States a specific verb ('Get') and resource ('detailed explanation of a DICOM tag') with clear scope. Effectively distinguishes from sibling 'lookup_dicom_tag' by emphasizing depth (vendor quirks, gotchas, context) versus simple 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?

Provides clear context about the richness of returned information (vendor quirks, common values, gotchas) which implies when to use it (for deep understanding/troubleshooting). Lacks explicit 'when not to use' or named alternatives, though the content description makes the distinction 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?

With no annotations provided, the description carries the full burden. It discloses the return structure (fields with positions, data types, etc.) but omits safety characteristics (read-only vs. destructive), error handling for invalid segment names, or idempotency guarantees.

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

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

Single dense sentence efficiently packs the purpose and detailed output specification. No filler words; every clause conveys essential information about the tool's function and return value structure.

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 absence of an output schema, the description adequately compensates by detailing the return value structure (positions, data types, optionality, etc.). However, it could be improved by mentioning error handling for unknown segment names or noting that this is a reference lookup operation.

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 the segment_name parameter fully documented in the schema. The description does not add additional parameter context (e.g., case sensitivity, valid character sets, or examples beyond those in the schema), meeting the baseline for high 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 tool explains HL7 segments and specifies the detailed output (fields, positions, data types, optionality, table references). This distinguishes it from sibling tools like parse_hl7_message or validate_hl7_message, though it doesn't explicitly name those 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 provides no guidance on when to use this tool versus alternatives like parse_hl7_message (for parsing instances) or lookup_hl7_table (for code lookups). It omits prerequisites or contextual triggers for 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?

With no annotations provided, the description carries the full burden and successfully discloses what the tool produces (message flow diagrams, expected segments, common pitfalls, best practices). This gives clear behavioral context about the output format. It does not clarify what [Premium] implies for access restrictions or rate limits, but covers the core behavioral traits.

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

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

The description is efficiently structured with the [Premium] tag and main purpose front-loaded, followed by a comprehensive list of content deliverables and valid pattern names. Every element earns its place; there is no redundant or wasteful 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?

Given the tool's single-parameter simplicity and lack of output schema, the description adequately compensates by detailing what the explanation will contain (diagrams, segments, pitfalls). For an educational tool of this scope, the description provides sufficient context for successful invocation, though it could note the output format 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?

While the schema has 100% description coverage with examples, the description adds significant value by enumerating the complete set of valid pattern options (seven specific patterns) beyond the schema's limited examples. This compensates for the lack of enum constraints in the schema and guides the user toward valid inputs.

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 specific verbs ('Explain') and resources ('healthcare integration patterns') and explicitly enumerates included content types (message flow diagrams, trigger events, best practices). It clearly distinguishes from operational siblings like parse_hl7_message or pacs_query by focusing on architectural/educational content rather than data processing.

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 an implicit usage guide by listing the seven supported pattern names ('ADT feed', 'order to result', etc.), indicating the tool handles these specific scenarios. However, it lacks explicit when-to-use guidance comparing this educational tool against its siblings or stating prerequisites for the [Premium] designation.

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

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

With no annotations, description carries full burden. It discloses output structure ('channel skeleton with source/destination connectors, transformer steps, filter logic, and implementation notes'), adding value beyond the schema. However, lacks safety profile (read-only vs destructive), persistence details, or scope limitations.

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 purpose. '[Premium]' prefix is minor clutter but second sentence efficiently lists output components. No redundant 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?

Adequate for a 3-parameter generation tool without output schema. Description compensates by detailing what the generated XML contains (skeleton components). Would benefit from noting whether output is returned as string or saved to file, but sufficient for agent selection.

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

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

Schema has 100% description coverage (source_type, destination_type, use_case all documented). Description mentions 'source/destination connectors' which conceptually maps to parameters but adds no syntax, validation rules, or format details beyond schema. Baseline 3 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?

Specific verb ('Generate') and resource ('Mirth Connect channel configuration XML') clearly stated. Distinguishes from siblings (all siblings are query/parse/explain tools; this is the only code generation tool for integration engine configuration).

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?

Implies usage context (creating Mirth channel skeletons) but lacks explicit when-to-use guidance or alternatives. No mention of whether to use explain_integration_pattern first, or when this generation might fail.

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

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

No annotations provided, so description carries full burden. Adds critical '[Premium]' access constraint and 'realistic' quality indicator, plus boundary constraints (supported message types list). However, omits error behavior for unsupported types, idempotency, quota/credit consumption, and output format 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?

Single sentence with zero waste. Front-loads '[Premium]' status and main verb, follows with supported types list. Every element earns its place; no filler text despite high information density.

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?

Appropriate for a 2-parameter tool without output schema. Covers core functionality, access level, and input constraints. Missing only error handling details and output structure description, which would be nice-to-have given the 'Premium' flag.

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

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

Schema has 100% description coverage (baseline 3), but description adds significant value by enumerating all supported message_type values (ADT^A01 through DFT^P03) which the schema doesn't constrain as enums. This specific list helps agents select valid inputs.

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?

Clear specific verb ('Generate') + resource ('sample HL7 messages') + context ('for testing'). The exhaustive list of supported message types (ADT^A01, ORM^O01, etc.) effectively distinguishes this from siblings like parse_hl7_message and validate_hl7_message.

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

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

Provides implied usage context ('for testing') but lacks explicit when-to-use/when-not-to-use guidance or named alternatives. Doesn't clarify relationship to generate_mirth_channel or when to use real vs. sample 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively compensates for the missing output schema by explicitly listing all returned fields (tag number, name, VR, VM, description, common values, usage notes), giving the agent clear expectations about the tool's 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?

The description is tightly structured with three distinct information units: purpose (sentence 1), return values (sentence 2), and input formats (sentence 3). Every clause earns its place with zero redundancy or filler text, presenting information in order of operational importance.

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 lookup tool with no annotations, the description is complete. It covers the tool's function, input flexibility, and return structure comprehensively. The absence of an output schema is adequately mitigated by the detailed return value description, making this sufficient for correct agent 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?

While the schema has 100% coverage and documents the basic parameter, the description adds valuable semantic context by specifying additional valid input formats, particularly the parenthetical syntax '(0010,0010)' which supplements the schema's examples. This helps the agent understand the flexible parsing capabilities.

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 specific action (Look up), target resource (DICOM tag), and input methods (group/element number or keyword). It effectively distinguishes from siblings like pacs_query (which retrieves studies) and decode_private_tags (specific to private tags) by focusing on standard tag dictionary 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 provides implied usage guidance through detailed input format examples ('0010,0010', '(0010,0010)', 'PatientName'), helping the agent construct valid inputs. However, it lacks explicit differentiation from the sibling explain_dicom_tag tool or clear when-to-use/when-not-to-use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully explains the return payload ('Returns the table name and all defined values with descriptions'), which is critical given the lack of an output schema. However, it omits other behavioral traits like whether the operation is idempotent, cached, or if there are 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 description is extremely tight: one sentence for the action, one for the return value, and a concrete example. Every element earns its place. There is no redundancy with the schema or unnecessary verbosity.

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 this is a simple single-parameter lookup tool without an output schema, the description adequately compensates by describing the return structure. It does not need to explain complex nested objects or error scenarios. For its complexity level, the description is complete, though usage guidelines would improve 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?

While the input schema has 100% coverage and already documents the table_number format (including examples like '0001'), the description adds valuable semantic context by specifying that Table 0001 corresponds to 'Administrative Sex.' This helps the agent understand what kind of data these tables contain beyond just the numeric identifier.

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 'Look[s] up HL7 table values' with a specific verb and resource type. It distinguishes itself from DICOM siblings (lookup_dicom_tag) and other HL7 siblings (explain_hl7_segment, parse_hl7_message) by focusing on 'tables' rather than segments or messages. The example (Table 0001 = Administrative Sex) clarifies the domain.

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 like explain_hl7_segment (which explains segment definitions) or other lookup tools. It does not specify prerequisites, such as needing a valid HL7 table number, or when to prefer this over parsing a message directly.

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

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

No annotations provided, so description carries full burden. Discloses return structure ('HL7 segment.field, mapping notes, and data type conversions') which is valuable without output schema, but omits safety properties (read-only status, idempotency) and operational constraints.

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 efficient sentences with zero waste. Front-loaded with purpose '[Premium] Map...' followed immediately by return value specification. Every clause delivers distinct value (operation, domain, return structure).

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 specialized medical informatics tool without output schema, adequately describes return values. Single parameter is well-documented in schema. Minor gap: [Premium] flag hints at access constraints but description doesn't elaborate on authentication or rate limiting implications.

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

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

Schema has 100% description coverage with examples ('0010,0010' or 'PatientName'). Description mentions 'DICOM tags' generally but does not augment parameter semantics beyond what the schema provides. Baseline 3 appropriate given schema completeness.

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?

Specific verb ('Map') with clear resources ('DICOM tags', 'HL7 v2 fields') and explicit scope. Distinguishes from sibling explain_dicom_tag (explains vs maps) and map_hl7_to_fhir (different source/target standards).

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

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

Provides clear domain context (DICOM-to-HL7 mapping) that implies usage, but lacks explicit when-to-use guidance versus alternatives like explain_dicom_tag or lookup_dicom_tag. No 'when-not' exclusions mentioned.

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

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

With no annotations provided, the description carries the full burden. It compensates by detailing the return structure (FHIR resource, element path, ConceptMap reference, conversion notes), but omits safety traits (read-only status), error handling behavior for invalid field_refs, or implications of the '[Premium]' tag (rate limits, access restrictions).

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 tightly constructed sentences with zero waste: first states the transformation purpose, second states the return values. The '[Premium]' tag is front-loaded and material to usage.

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 conversion tool without output schema, the description adequately covers the conversion direction, FHIR version specificity (R4), and return value structure. Minor gap in not describing error scenarios or validation behavior.

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%, providing complete parameter documentation. The description mentions 'segments/fields' generally but does not add semantic context, constraints, or format guidance beyond what the schema already specifies for 'field_ref'.

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 ('Map') and clear resource types ('HL7 v2 segments/fields' to 'FHIR R4 resources'), distinguishing it from siblings like 'map_dicom_to_hl7' (different direction/format) and 'explain_hl7_segment' (explanation vs. conversion).

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 through the specific domain (HL7-to-FHIR conversion), but provides no explicit 'when to use' guidance, prerequisites (e.g., understanding SEGMENT-POSITION format), or alternatives to this mapping approach.

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

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

With no annotations provided, the description carries the full burden and succeeds in disclosing the mechanism (C-ECHO/HTTP ping) and return values (success/failure, response time, connection details). Could be improved by mentioning timeout behavior or whether this requires specific network permissions.

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?

Perfectly structured: premium tag, one-sentence purpose, mechanism explanation, and return value disclosure. No wasted words; every clause adds necessary context beyond the structured fields.

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 zero-parameter tool without an output schema, the description adequately compensates by detailing the return values in text. Would benefit from mentioning error conditions or timeout handling, but sufficient for the tool's complexity.

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?

Input schema has zero parameters, establishing a baseline of 4. The description appropriately focuses on behavior and outputs rather than inventing parameter documentation where none exists.

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?

Excellent specificity: 'Verify PACS connectivity' uses a clear verb + resource, and the mention of 'C-ECHO (DIMSE) or HTTP ping' technically distinguishes this from siblings like pacs_query and pacs_retrieve which perform data operations rather than connectivity checks.

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

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

Provides implied usage context ('confirm the PACS server is reachable'), suggesting when to use it (before data operations), but lacks explicit guidance like 'Use this before pacs_query' or warnings about when not to use it vs. alternatives.

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

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

With no annotations provided, the description carries the full burden. It successfully discloses the return content (DICOM header information with specific categories) and implementation protocols (WADO-RS metadata or DIMSE C-FIND). The '[Premium]' tag indicates access restrictions. However, it lacks details on error handling, rate limits, or response format specifics.

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 efficiently structured across three sentences: the first establishes the core action and access tier ([Premium]), the second details the return payload, and the third specifies the underlying protocols. Every sentence provides distinct value with no 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 absence of an output schema, the description adequately compensates by enumerating the categories of returned DICOM header information. It covers the essential behavioral and protocol context for a 2-parameter read operation. A minor gap remains regarding error conditions or explicit return format specifications.

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

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

The input schema has 100% description coverage, establishing a baseline of 3. The description mentions 'study or series' which aligns with the two parameters (study_instance_uid and series_instance_uid), but does not add semantic clarification, examples, or format constraints 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 provides a specific verb ('Retrieve'), clear resource ('detailed metadata for a study or series from PACS'), and distinguishes from siblings like pacs_retrieve and pacs_query by specifying it returns 'DICOM header information' and uses specific protocols (WADO-RS metadata/C-FIND) rather than image retrieval or general study search.

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

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

The description provides clear technical context that distinguishes this tool—specifying it returns DICOM header details (patient, study, series, equipment) and uses WADO-RS metadata or C-FIND protocols. This implies when to use it (when header metadata is needed, not images). However, it lacks explicit 'when not to use' guidance or named alternatives (e.g., 'use pacs_retrieve for image 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?

No annotations provided, so description carries full burden. It adds crucial behavioral context: the 50-result limit, '[Premium]' tier indicator, and underlying protocols (C-FIND/QIDO-RS). However, it omits safety disclosure (read-only nature), authentication requirements, and what the results contain given no output schema exists.

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?

Well-structured and front-loaded with the '[Premium]' tag and primary purpose. Four sentences efficiently convey scope, filters, limits, and implementation details. Minor redundancy in listing all filter fields that are already well-documented in the schema, but this aids scannability.

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 9 parameters and no output schema, the description adequately covers input capabilities but only minimally addresses return values ('Returns up to 50 results' without describing structure or fields). Given the medical domain complexity, it should describe the return format or study/series object structure since no output schema compensates.

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?

Input schema has 100% description coverage, establishing baseline 3. The description lists the available filters but adds no semantic meaning beyond what the schema already provides (e.g., date format YYYYMMDD is documented in both). No additional parameter syntax or examples are provided.

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

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

Clearly states the tool searches PACS for studies or series with specific filtering capabilities. However, it does not explicitly differentiate from sibling tools like 'pacs_retrieve' or 'pacs_study_summary', though the verb 'Search' implies read-only query vs. retrieval.

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

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

Provides implied usage through the specific mention of C-FIND/QIDO-RS protocols (query operations) which distinguishes it from retrieval operations. However, lacks explicit guidance on when to use this versus 'pacs_retrieve', 'pacs_get_metadata', or 'pacs_study_summary' for users unfamiliar with DICOM protocol differences.

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

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

With no annotations, the description carries the full burden. It discloses network side effects ('moves real images across the network') and configuration prerequisites, but omits execution details like synchronous/asynchronous behavior, error handling, return values, or idempotency characteristics crucial for a network mutation operation.

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 sentences with zero waste: front-loaded action ('Initiate C-MOVE...'), safety warning, protocol constraint, and configuration prerequisite. The '[Premium]' tag efficiently signals feature gating without verbosity.

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 complex network operation with side effects and no output schema, the description should describe success indicators or return behavior. It adequately covers prerequisites and safety but leaves the agent unaware of what constitutes successful invocation or failure modes.

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%, establishing a baseline of 3. The description mentions 'C-MOVE' which provides protocol context for the UID parameters, but does not add semantic details beyond the schema (e.g., AE title formatting rules, UID syntax constraints, or examples).

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

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

The description clearly states the specific action ('Initiate C-MOVE'), resource ('images from PACS'), and destination ('destination AE title'). Mentioning 'C-MOVE' specifically distinguishes it from sibling query tools like pacs_query (likely C-FIND) and pacs_echo.

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

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

Provides explicit constraints ('Only available via DIMSE protocol', 'Requires DICOM_HL7_PACS_ALLOW_RETRIEVE=true') and safety warnings ('use with care'). Lacks explicit contrast with siblings (e.g., when to use query vs retrieve), but the technical prerequisites serve as clear usage gates.

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

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

With no annotations provided, the description carries full burden. It clearly enumerates the four return components and uses 'Query' implying read-only behavior, but omits explicit safety declarations, error handling (e.g., study not found), rate limits, or whether the '[Premium]' label affects access/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?

Front-loaded with the core action and well-structured with the '[Premium]' tag, main function sentence, return value enumeration, bridge metaphor, and input clarification. Slightly redundant in mentioning search parameters at the end since the schema already documents them, but overall efficient for the complexity described.

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 lack of an output schema, the description adequately compensates by detailing the four complex return structures (including specific message types like ORM^O01). However, it could improve by noting that at least one identifier is logically required (despite schema showing 0 required parameters) or describing error response behavior.

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

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

Schema has 100% description coverage for both parameters ('Study Instance UID to look up' and 'Accession number to look up (alternative to UID)'). The description adds minimal semantic value beyond the schema, merely confirming 'Search by Study Instance UID or accession number' without adding format constraints, validation rules, or examples.

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

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

Description explicitly states the tool 'Query[ies] a study from PACS and show[s] its complete interoperability mapping' and distinguishes from siblings by detailing four specific return components (metadata, DICOM-to-HL7 mapping, HL7-to-FHIR mapping, and HL7 ORM^O01 skeleton) that combine functionality of separate 'map_*' and 'pacs_*' tools into a single interoperability bridge.

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

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

Provides implied usage context by describing itself as 'the bridge between what's in PACS and how do I represent it in HL7/FHIR', but lacks explicit guidance on when to choose this comprehensive tool over simpler alternatives like 'pacs_get_metadata' or the individual 'map_dicom_to_hl7' and 'map_hl7_to_fhir' 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?

With no annotations provided, the description carries the full burden and succeeds in detailing the transformation behavior: it performs 'table lookups' and provides 'explanations' beyond raw parsing, and specifies supported segments. It implies read-only behavior ('Parse... Returns'), though it could explicitly state safety properties or error handling for invalid messages.

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 with zero waste: sentence 1 defines the core action, sentence 2 describes the return value, and sentence 3 lists specific segment support. Information is front-loaded with the essential verb and resource immediately stated.

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

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

Despite lacking an output schema, the description compensates by detailing the return structure ('parsed segments with field names, values, table lookups, and explanations'). The input parameter is fully documented in the schema. Minor gap: no explicit read-only declaration given the absence of safety annotations.

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%, providing the baseline. The description aligns with the schema by mentioning 'HL7 v2.x message' but does not add parameter-specific semantics beyond the schema's details about pipe-delimiters and segment separators. The segment list (MSH, PID, etc.) relates to capability rather than 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 ('Parse') with clear resource ('HL7 v2.x message') and output format ('human-readable'). It distinguishes from siblings like 'validate_hl7_message' (validation vs parsing) and 'explain_hl7_segment' (single segment vs full message) by emphasizing full message parsing with specific segment examples (MSH, PID, etc.).

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 through the output specification ('Returns parsed segments...'), but lacks explicit when-to-use guidance versus alternatives. It does not indicate whether to use 'validate_hl7_message' first, or when 'explain_hl7_segment' might be preferable for single-segment analysis.

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

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

With no annotations provided, the description carries the full burden. It successfully discloses the validation scope (5 specific check types) and the '[Premium]' prefix signals potential access restrictions. However, it lacks explicit statements about whether the operation is read-only or what happens on validation failure (error throwing vs. error reporting).

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 efficiently structured with the '[Premium]' tag front-loaded, followed by a clear purpose statement and a specific enumeration of validation behaviors. Every sentence contributes essential information without 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 absence of an output schema, the description should ideally specify the return format (e.g., error list, boolean, validated object) for a validation tool. While the validation scope is well-defined, the lack of output specification leaves a significant gap for agent invocation handling.

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

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

The input schema has 100% coverage with a clear description ('Raw HL7 v2.x message string to validate'). The tool description references the message but does not add semantic meaning, format constraints, or examples beyond what the schema already provides. Baseline 3 is appropriate for high 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 states the specific action ('Validate') and resource ('HL7 v2.x message') clearly. The phrase 'against the standard' and the detailed list of validation checks (required fields, data types, etc.) effectively distinguish this tool from the sibling 'parse_hl7_message', which likely only extracts structure without compliance checking.

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?

While the description implies usage through the detailed validation criteria (use when you need standard compliance checking), it lacks explicit guidance on when to choose this over 'parse_hl7_message' or other siblings. There are no stated prerequisites or conditions for when this tool is inappropriate.

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