Server Quality Checklist

Tool Scores

• fleet_listA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds useful context about the contents of the list ('current published... daily rates, mileage terms, photos, booking URLs') but does not disclose behaviors like pagination or all-vs-partial listing beyond what the annotations imply.

  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?

  A single sentence leads with the verb and resource, then enumerates the relevant data fields. No filler or repetition; every phrase earns its place.

  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?

  The tool is a simple zero-parameter list with a strong annotation set and an output schema present. The description fully covers what the agent needs to know to invoke it: what resource is listed and what data will be returned.

  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 has zero parameters, so there are no parameter semantics to document. The rubric sets a baseline of 4 for a zero-parameter tool, and the description's content coverage makes this 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?

  Begins with the specific verb 'List' and identifies the exact resource, 'current published Sketchy Rides LA fleet,' plus the data included (daily rates, mileage terms, photos, booking URLs). This distinguishes it from sibling tools like quote_trip or availability_check, which serve different purposes.

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

  Usage Guidelines3/5

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

  The description implies the use case—call this when the agent needs the current published fleet listing—and the 'current published' wording sets scope. However, it does not explicitly state when to choose fleet_list over search, fetch, availability_check, or quote_trip, nor does it list exclusions.

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

• quote_tripA
  4.1/5.0
  Behavior4/5

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

  The description discloses meaningful behavior beyond the annotations: the quote includes daily rate, insurance plan, 11.5% CA tax, and deposit hold, and the insurance fee is only a demo charge, not issued coverage. This complements the readOnlyHint and idempotentHint annotations without contradicting them.

  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 compact and front-loads the formula and quote type before the plan options and caveat. The 'Pilot' typo is a minor readability issue, but the description remains focused with no wasted words.

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

  Completeness4/5

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

  With an output schema and readOnly/idempotent annotations present, the description covers the important behavioral specifics: cost formula, tax, deposit hold, and demo insurance. It does not address car/start/end parameter formats or compare explicitly to sibling tools, but it is still sufficiently complete for the agent to call it correctly.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It usefully documents the plan parameter's allowed values ('full | liability | decline') and clarifies how cost components fit together. However, it leaves car, start, and end semantics to inference, with no format or meaning beyond their identifiers.

  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?

  It names a specific action ('exact checkout quote'), the exact resource being quoted, and the financial inputs that compose the quote. This clearly distinguishes it from sibling tools like availability_check or fleet_list.

  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 makes the intended use clear: produce a precise checkout price in USD cents. It does not explicitly discuss alternatives or when not to use this tool, but the context is strong enough that an agent can infer the right scenario.

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

• fetchA
  4.2/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context beyond those: it returns the full text of exactly one page, and the id is a search-result URL. This is not contradictory with 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?

  A single, front-loaded sentence with no filler: action, resource, and input all appear immediately. Every word 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 one-parameter, read-only tool with an output schema present, the description is nearly complete: it covers input provenance, scope, and result type. The only minor gap is an explicit statement about when to choose fetch over the sibling search tool, but the wording already implies that.

  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 gives only a bare string field with 0% description coverage, so the description must provide meaning. It does so by clarifying that 'id' is a URL from search, which tells the agent exactly what value to supply. It does not cover edge cases like URL encoding or invalid ids, but for a single input it is sufficiently contextual.

  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 action ('Fetch'), a specific resource ('full text of one site page'), and a clear identifier ('its id (a URL from search)'). This distinguishes it from siblings like search (which discovers pages), fleet_list, availability_check, and quote_trip.

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

  Usage Guidelines3/5

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

  The parenthetical '(a URL from search)' implies the natural usage context: call this after search when you have an id and need a page's full text. However, it does not explicitly state when not to use it or name alternatives, leaving routing partly to inference.

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

• availability_checkA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, covering the safety and world-view. The description adds useful behavioral context beyond those: it specifies the input format (car slug or VIN, YYYY-MM-DD dates) and clarifies that 'end = return day'. This goes beyond what the schema or annotations provide, though it doesn't discuss edge cases like timezone or inclusivity of dates.

  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 extremely concise—two sentences—and front-loads the core purpose. The parameter explanation is compactly packed into a single line using separators (·). Every sentence earns its place with no redundancy or 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 simple availability check with an output schema, the description covers the essential semantics and parameter meanings. It might be improved by noting whether the result is a boolean or includes availability windows, but the output schema likely handles that. Minor gaps like timezone assumptions or inclusive/exclusive date boundaries are not addressed, but these are not critical for the tool's core function.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description carries the full burden of explaining parameters. It does so completely: 'car' is identified as a slug or 17-char VIN, and 'start'/'end' are YYYY-MM-DD dates with the note that 'end = return day'. Every parameter is explained with both format and meaning, fully compensating for the bare 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 uses a specific verb ('Check') and clearly states the resource ('whether a car is free for a date window'). It distinguishes itself from siblings like fleet_list (listing) and quote_trip (pricing) by focusing on availability, so an agent can select it correctly without ambiguity.

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

  Usage Guidelines3/5

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

  The description clearly implies the use case (checking availability), but it does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The agent must infer that this is the go-to tool for availability checks based on the purpose alone.

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

• searchA
  4.3/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: it returns lightweight result objects, not full page text, and requires a follow-up fetch call to retrieve complete content.

  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 a single well-structured sentence that front-loads the core purpose, includes the return shape, and closes with the follow-up action. Every phrase earns its place with no wasted words.

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

  Completeness5/5

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

  For a simple search tool with one parameter, rich annotations, and an output schema, this description is complete. It tells the agent what is searched, what the result shape looks like, and what to do next to get full content.

  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 0%, so the description must compensate for the undocumented query parameter. The description implies that 'query' is the search text for the public site, but it does not provide examples, syntax expectations, or any guidance on how the query is matched. This is adequate for a single obvious string parameter but not rich.

  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 that this tool searches the public Sketchy Rides site and lists the content types it covers. It also distinguishes itself from the sibling tool fetch by explicitly saying that fetch(id) should be called for full page text, making its role unique.

  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 gives clear context for when to use search — to discover pages across rental terms, fleet pages, destination guides, and blog posts — and instructs the agent to call fetch(id) for full content. It does not explicitly mention exclusions for other siblings like availability_check or quote_trip, but the search-vs-fetch workflow is clearly implied.

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