Server Quality Checklist

Tool Scores

• usace_rivermile_find_markersA
  4.3/5.0
  Behavior4/5

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

  The annotations already state readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds value beyond annotations by explaining that results for point queries include 'distance_m' and are sorted nearest-first, that geometry queries return intersecting markers, and that the 'truncated' field indicates more matches exist. It also lists error responses. This is above and beyond what annotations provide, though the output schema (which exists) already documents the return format, slightly reducing the need for that detail.

  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 well-structured with clear sections (purpose, usage patterns, return format, error responses). It is fairly concise for the amount of information provided, but could be slightly trimmed (e.g., the full error list could be summarized as 'See error responses: ...'). Still, nearly every sentence earns its place.

  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, 100% schema coverage, a detailed output schema, and comprehensive annotations, the description is nearly complete. It explains the two usage modes, result sorting, truncation behavior, and error cases. The only minor gap is that it does not explicitly state what happens when no markers are found (though the output schema structure implicitly shows count=0). Overall, very well-rounded.

  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 description coverage is 100%, providing solid baseline. The description adds limited extra semantics beyond the schema—it explains the dual-mode logic and gives usage examples, but the schema already covers descriptions for each parameter decently. The description does not add new constraints or format details for parameters that aren't already in 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 specifies 'Find USACE river mile markers near a point or within a geometry', using a specific verb ('Find'), a distinct resource ('USACE river mile markers'), and the operation's dual modes (point+radius or geometry). It explicitly distinguishes itself from siblings by not being the 'nearest' or a generic 'query' tool.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance with concrete query examples for both lat/lon and geometry modes, and clearly warns 'supply either lat+lon or geometry, not both (or neither)'. This fully addresses when and how to choose between usage patterns, earning a top score.

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

• usace_rivermile_nearestA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is clear. The description adds substantial behavioral detail beyond annotations: it explains the search logic (nearest within radius, great-circle distance calculation), the return structure including bearing and plain-language finding, and error response format. This is valuable context that complements 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.

  Conciseness5/5

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

  The description is concise and well-structured. It leads with the core purpose in the first sentence, then provides a clear example of the JSON return and error format. Every sentence serves a purpose, and the structure allows quick scanning for an agent. No wasted text.

  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?

  Given the low parameter count (3), full schema coverage, presence of annotations, and output schema, the description is complete. It covers the core logic, return structure, error handling, and provenance information. An agent has all necessary context to invoke and correctly interpret results.

  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 description coverage is 100%, so baseline is 3. The description does not add new parameter-level detail beyond what the schema provides; it only reiterates the max_radius_meters search behavior. The lat/lon parameters are not elaborated beyond the schema. Thus, the description adds marginal value to parameter understanding.

  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 starts with a clear verb and resource: 'Return the single closest river mile marker to a WGS84 coordinate.' It pinpoints the exact operation (find nearest) and resource (river mile marker), and implicitly distinguishes from siblings by focusing on 'single closest' rather than listing or querying multiple markers.

  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 frames the use case: 'Answers "what river mile am I at?" / "nearest marker to this point"', providing clear context for when to use this tool. It also mentions the max_radius_meters search boundary. However, it does not explicitly indicate when NOT to use (e.g., if multiple markers are needed) or reference sibling tools as alternatives, leaving a slight gap in exclusion guidance.

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

• usace_rivermile_queryA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is clear. The description adds useful behavioral details: results are ordered by MILE ascending, paginated via offset with total_count and next_offset, and a 'where' field is included for transparency. It also documents three specific error responses. Minor gap: no mention of rate limits or data staleness, but overall strong for a read-only query tool.

  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 well-structured with clear sections: purpose, usage examples, pagination semantics, output format, and error responses. Every line is informative, and the examples are front-loaded. At about 20 lines, it's appropriately sized without redundancy.

  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?

  Given the tool has 5 parameters with 100% schema coverage, an output schema that documents the return structure, and clear annotations, the description is complete. It covers pagination behavior, error handling, filter constraints, and response structure. No gaps remain for effective agent decision-making.

  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 coverage is 100%, so baseline is 3. The description adds value by showing example values (e.g., 'RED', 'MISSISSIPPI', 'OHIO') for river_name, clarifying inclusive bounds for mile_min/mile_max, and demonstrating usage patterns (e.g., 'mile_min=900'). It also explains the interplay between filters ('provide at least one filter'). However, it doesn't add new parameter semantics beyond what the schema already provides, so a 4 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 queries USACE river mile markers by river name and/or mile-value range, using specific verbs like 'Query' and 'List'. It distinguishes from siblings by mentioning filtering by river and mile range, while sibling names like 'find_markers' and 'nearest' imply different use cases.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use the tool with example queries ('List markers on the RED river', 'How many markers on the Mississippi between mile 400 and 600?') and provides a clear alternative pattern (mile_min=900). It does not mention siblings directly but implies when to use this vs other tools by its focus on combined river and mile filtering.

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