Server Quality Checklist

Tool Scores

• export_quality_plan_excelA
  3.5/5.0
  Behavior3/5

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

  Annotations already mark this as a non-read-only, idempotent, non-destructive, closed-world write, so the safety profile is covered. The description adds genuine behavioral value by detailing what ends up cell-for-cell in the workbook, but says nothing about whether the drawing/PDF files are touched, what happens if the target file already exists (that is schema-only), or what the call returns (e.g. the written path).

  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?

  One front-loaded sentence opens with the verb and artifact, then spends the rest on a concrete manifest of report contents; a short second sentence covers the default location. The column enumeration is long but defensible since it defines the deliverable, and there is no boilerplate filler.

  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 complex, nested-schema export tool with no output schema, the description conveys what the generated artifact contains, its naming convention, and its default location, which is what an agent needs before invoking. It is slightly short on cross-tool sequencing (analyze/load → build_quality_plan → export) and on the return value.

  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 every parameter including the deeply nested plan object is already documented at source; the description does not need to compensate. It adds only the path-convention detail (<drawing number>_<inspection class>.xlsx) which partially overlaps the output_path description, so it does not meaningfully exceed the schema.

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

  Purpose4/5

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

  States a specific verb and artifact — write the quality plan as the "Measurement and inspection report" workbook (.xlsx) — and enumerates the exact sections produced. The Excel-vs-PDF distinction from export_inspection_pdf is implied by the format and content but the sibling is never named, so an agent must infer the routing.

  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 only implied: you call this when you want the report as a spreadsheet. There is no explicit statement of when to prefer this over export_inspection_pdf, no prerequisite about having a plan built first, and no note on when overwriting is appropriate (that lives only in the schema). The default-location sentence is the only concrete operational guidance.

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

• export_inspection_pdfA
  3.6/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=false with destructiveHint=false and idempotentHint=true, and the description usefully reinforces this with "The source PDF is never modified" plus the default write location and derived filenames. It adds real behavioral context beyond the annotation flags, though it does not mention what happens on a filename collision or what it returns.

  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 core action is front-loaded in the first clause and the remaining sentences each carry distinct information about the variants and the untouched source file. It is dense rather than bloated, though the run-on variant sentence with quoted labels is harder to scan than a short list would be.

  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 write tool with a large nested plan object, the description covers the highest-risk ambiguity (which PDF you get) and the source-file safety guarantee. With no output schema, the one remaining gap is that it never says what the call returns or how to reference the written file, which an agent would need for a follow-up step.

  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%, so the baseline is 3, but the description adds genuine value by spelling out what each variant actually renders and by giving the output filename convention per variant (<drawing number>_inspection-package.pdf / _ballooned.pdf / _quality-plan.pdf), which the schema only alludes to via 'default package'.

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

  Purpose4/5

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

  The opening "Write the inspection PDF" gives a specific verb+resource, and the three variant descriptions pin down exactly what artifacts are produced (marked-up drawing pages, plan document, or both). It does not, however, distinguish this tool from its sibling export_quality_plan_excel, leaving the agent to infer the PDF-vs-Excel split from names alone.

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

  Usage Guidelines2/5

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

  The description explains what each variant outputs but never states when to choose this tool over build_quality_plan or export_quality_plan_excel, nor any prerequisites beyond the optional pdf_path note. Variant selection guidance is present, but tool-selection guidance is absent.

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

• load_analysisA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this with 'Fully offline — no upload, no daily credit,' which is genuine cost/side-effect context beyond the annotations. It notes the registration side effect on plan/export tools, though it doesn't detail what happens on a duplicate or invalid analysis.

  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?

  Three tight sentences, front-loaded with the core action, then the offline/cost note, then the pdf_path tip. No padding, though the middle sentence interrupts the primary how-to flow slightly.

  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 read/register tool with no output schema and full schema coverage, the description covers source formats, prerequisites, cost profile, and the optional-but-advised pdf_path. It lacks detail on error behavior (missing/invalid analysis file) and the exact return, but annotations carry the safety profile and nothing essential to invoking it correctly is missing.

  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 all three parameters are already documented in the schema. The description adds the rationale for pdf_path (needed for ballooned/package PDF exports and writing next to the original), which slightly exceeds the schema, but the baseline for full schema coverage is 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?

  States a specific verb (open/register) with the resource (a previously saved analysis JSON), and explicitly distinguishes the two source formats (analyze_drawing save output vs. Imnoo FileStore analysis document). It also names the downstream effect — registering as a drawing usable by plan and export tools — which separates it from the analyze_* sibling.

  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?

  Gives a clear precondition (an analysis saved earlier via analyze_drawing with save_analysis_to) and the alternative source. It also advises passing pdf_path so exports work. However, it does not state when NOT to use this tool versus re-running analyze_drawing, so exclusions are implicit.

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

• build_quality_planA
  4.3/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true and openWorldHint=false, and the description corroborates with 'deterministic and offline' plus the iterate-then-export workflow, making clear the call is a non-persisting preview that is safe to repeat. It does not add auth, rate, or side-effect detail beyond that, but the annotation-consistent framing is genuinely useful.

  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?

  Two sentences, front-loaded with the output and its distinguishing scope, with the workflow constraint second. The first sentence is dense with enumerated plan contents but each clause maps to real behavior rather than filler.

  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 a large nested options object and no output schema, the description explains what the plan contains and that it is deterministic/reproducible, and points to drawing_id's provenance via analyze_drawing/load_analysis. It never sketches the returned plan shape, which is the only real gap.

  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 the schema already documents every field; the description adds value by framing the plan object as 'shared by build_quality_plan and both export tools' and summarizing what the options drive (balloon numbering, computed acceptance limits, default instruments, class/rate, section order). It stops short of adding syntax or format detail 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?

  States a specific verb and resource ('turn an analysed drawing into the quality control plan') and immediately scopes it as the plan 'the documents will print', which separates it from the sibling export tools that render that plan. An agent can tell what it produces without opening the schema.

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

  Usage Guidelines4/5

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

  Gives an explicit workflow: 'adjust the plan options and call again until the plan is right, then pass the same options to the export tools', which positions it as the step before the export siblings. It does not name the export tools explicitly or state when not to use it, so it falls short of full alternative routing.

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

• analyze_drawingA
  4.8/5.0
  Behavior5/5

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

  Beyond the annotations (openWorldHint, non-idempotent), the description discloses latency (20–120 s), timeout semantics (waits up to timeout_seconds, else returns "processing" with a drawing_id), rate limits, and the privacy/retention behaviour of uploaded files. These are exactly the traits an agent needs before committing to a slow, non-idempotent upload.

  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?

  Front-loaded with the extraction payload and then the operational constraints, and every clause carries information. Minor waste: the second sentence opens by restating 'analyze_drawing uploads the PDF to Imnoo's drawing analysis' before pivoting to the new rate-limit and retention facts, and the long characteristic enumeration is dense.

  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?

  There is no output schema, so the description carries the full return-value burden — and it does: per-characteristic feature id, value, PDF page, position and balloon number, plus the title block fields, and the "processing" fallback state. Combined with the timeout and resume mechanics, nothing needed to call or interpret this tool is missing.

  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%, so the baseline is 3; the description goes further by explaining the consequence of timeout_seconds (returning "processing" rather than failing), the resume semantics of drawing_id, and the offline-reuse purpose of save_analysis_to. It adds genuine meaning beyond the field descriptions, though it does not restate size/type limits.

  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 names a specific verb and resource (analyse a technical-drawing PDF) and enumerates exactly what is extracted: dimensional tolerances, ISO fit classes, threads, GD&T frames, surface finishes, plus title-block fields. This is far more specific than any sibling (load_analysis, build_quality_plan, export_*), so an agent can select it unambiguously.

  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?

  It states the two entry paths explicitly: upload via pdf_path, or resume an in-flight analysis via drawing_id when a prior call returned status "processing". It also routes to alternatives by name — save_analysis_to/load_analysis for offline reuse — and flags the rate-limit condition (1 free analysis/day per IP, more when signed in).

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