Server Quality Checklist

Tool Scores

• rechtspraak_cijfersA
  4.7/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool has no parameters, requires no key, and sends no text, which clarifies its side-effect-free nature. It also enumerates the exact data it returns (metrics, leakage, baseline), giving a clear picture of behavior. It does not explicitly state the return format, but the listed contents suffice for a zero-parameter retrieval 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 dense but every sentence earns its place. It front-loads the primary function, then lists the specific metrics, then gives usage guidance and a critical caution about the baseline, and finally states operational facts. No fluff or redundancy; the structure guides the reader logically from what to why to how.

  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 tool with no parameters and no output schema, the description is complete: it fully describes what the tool returns (all benchmark figures), when to use it, when not to, and important caveats (baseline alongside accuracy). An agent can invoke it correctly and interpret the output without ambiguity. Nothing essential 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?

  The tool has 0 parameters and the schema is empty, so the description confirms this with 'Geen parameters'. It adds that no key is needed and it sends no text, which is useful operational context beyond the schema. Since there are no parameters to describe, this baseline of 4 is appropriate and the description adds value.

  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 explicitly states the tool's purpose: providing benchmark figures behind voorspel_uitkomst. It lists specific metrics (accuracy, macro-F1, F1 per class, label distribution, leakage, baseline) and clearly distinguishes it from siblings by stating it is not for assessing cases (voorspel_uitkomst) or measuring text (lekkage_check). This makes the purpose unambiguous and differentiates it from all siblings.

  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?

  Usage guidance is explicit: 'Use this if someone asks how good the model is, or to check a figure before citing it — not to assess a case (that is voorspel_uitkomst) or to measure text (lekkage_check).' It also provides a critical rule: the baseline must always accompany accuracy, preventing misuse. This is clear when/when-not guidance with named alternatives.

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

• lekkage_checkA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so thoroughly: it explains the cut rule (including the 300-character lead, the <200-character exception, and the dictum detection), what 'clean' means, the return values (length, categories, and what remains), that no key is needed, and the privacy implication that text is sent to a server. It even notes that longer text is rejected before transmission, a behavioral edge case.

  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 dense but each sentence earns its place, covering purpose, algorithm, usage, returns, authentication, and privacy in a logical order. It is not overly verbose given the complexity, though it could be slightly more concise by merging some clauses. The front-loading of purpose and the cut rule is effective.

  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 measurement tool with no output schema and no annotations, the description is remarkably complete. It covers the input, the algorithm, the return format (including category names), the usage context, authentication (no key), and a critical privacy caveat. An agent can invoke it correctly and interpret the result without external knowledge.

  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?

  The schema covers the parameter fully (tekst, maxLength, plain text), so the baseline is 3. The description adds value by advising to supply a full statement ('geef een volledige uitspraak mee') and explaining why short fragments may be unmeasurable, which helps the agent provide an appropriate input. It also reinforces the max-length rejection behavior, which is not in 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?

  The description states a specific action: measuring whether a text's reasoning reveals its outcome, using a defined 'lekkage-knip' (cut) that removes the dictum and preceding characters. It explicitly distinguishes itself from the sibling tool voorspel_uitkomst by noting it is a measurement, not a prediction, which fully disambiguates the purpose.

  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 clearly states when to use this tool: to test a dataset, benchmark, or an AI claim, and explicitly says to use voorspel_uitkomst instead when an outcome judgment is desired. It also advises to provide a full text because a short fragment may leave nothing to measure, giving concrete usage guidance.

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

• voorspel_uitkomstA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full behavioral burden, and it does so richly: it explains the server-side leakage clipping workflow, model performance, returned fields, the 55% confidence threshold, API-key requirements, rate limits, external data transmission, and the non-advice/non-judicial-use disclaimer.

  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 long but information-dense, with each block serving a purpose: purpose, sibling routing, method/performance, output shape, threshold, auth, and privacy. It is front-loaded with the core purpose. There is slight redundancy between the initial 'Gebruik dit' sentence and the later 'Kies deze tool' routing, so it is not maximally tight.

  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 no annotations and no output schema, the description covers everything an agent needs to invoke the tool correctly and interpret its result: input constraints, failure cases, required environment variable, rate limiting, output fields, confidence threshold, privacy implications, and alternative sibling tools.

  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?

  The input schema already describes both parameters at 100% coverage, so the baseline is 3. The description still adds value by specifying the 200-character post-clipping minimum, clarifying that dictum/outcome sentences can remain because they are removed server-side, and giving the exact class labels returned.

  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 first sentence names a concrete action ('Voorspelt de afloop'), a specific object ('Nederlandse rechtszaak uit de zaaktekst'), and the exact output classes ('afgewezen, gedeeltelijk of toegewezen'). It also explicitly separates this tool from its siblings, so an agent can distinguish it without opening their schemas.

  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 choose this tool ('als je een oordeel over de afloop wilt'), when to use lekkage_check instead, and when to use rechtspraak_cijfers. It also gives concrete input requirements: use a full case text, not a short summary, and keep at least 200 characters after trimming.

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