Server Quality Checklist

Tool Scores

• species_seasonalityA
  3.5/5.0
  Behavior3/5

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

  The caveat "Recorded sightings, never a promise of encounters" is a strong behavioral disclosure, and naming GBIF as data source adds useful context. With no annotations present, though, the description does not explain how coordinates affect the regional windows, whether unsupported species return empty or error, or what the actual output contract looks like.

  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 only two sentences, front-loading the key output before adding the caveat. Every sentence adds value, and the structure makes the non-guarantee of sightings hard to miss.

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

  Completeness2/5

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

  The description covers the headline output and data source, but with no output schema and no annotations, the agent is left with too many unknowns: how lat/lng alter regional windows, what set of species is supported, and whether the result is a ranking, a calendar representation, or something else. It is adequate for a first understanding, but not enough to call with confidence in less-common coordinate-specific requests.

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

  Parameters2/5

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

  Schema coverage is only 33%, and the description does not compensate by explaining the optional lat and lng parameters. It mentions regional season windows but never connects them to the coordinate inputs, leaving an agent to guess how lat/lng refine the result. Only species is meaningfully described, via examples 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 clearly states what the tool provides: a month-by-month seasonality view with peak month and regional season windows for marquee dive species. It also differentiates from sibling tools by focusing on species-specific GBIF sightings rather than general dive windows, site facts, or best-time-to-dive lookup.

  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 use case is implied by the description: an agent should call this when a user wants species-level seasonality or peak encounter windows. However, the description never names alternatives like find_dive_windows, best_time_to_dive, or site_facts, nor does it state when those are more appropriate.

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

• best_time_to_diveA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It responsibly discloses that data is historical, not forecast, and requires citing the linked page. Still, it does not mention potential limitations like insufficient historical data, ambiguous destination names, or how 'favorable' is defined, leaving some behavioral ambiguity.

  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 compact and front-loaded: it states the core concept at the beginning, then adds examples, data scope, and a citation instruction. No words feel wasted; the extra context fits naturally into one sentence.

  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 single-parameter informational tool, the description covers inputs, outputs, limitations, and the citation requirement. It lacks an output schema and doesn't detail the return format, but the content described ('share of days', water temperature, marine-life windows) is enough for an agent to judge the tool's suitability.

  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 coverage is 0% and the only parameter is just a string named 'destination.' The description compensates somewhat by explaining it can be a country or famous destination and gives three examples, but it does not clarify exact name formats, case sensitivity, or whether destinations like 'Red Sea' are countries. This is helpful but incomplete.

  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 description clearly identifies the resource: month-by-month climatology for a single destination, with examples (Komodo, Cozumel, Red Sea) and the output content (favorable days, water temperature, marine-life windows). It does not use a strong imperative verb like 'get' or 'calculate,' but the purpose is unmistakable and generally distinct from siblings like top_dive_regions.

  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 emphasis on 'ONE destination' and 'never a forecast' establishes clear context and explicit when-not cases, ruling out multi-destination comparisons and future predictions. However, it does not explicitly name or route to sibling tools such as top_dive_regions or species_seasonality, so the guidance is contextual rather than fully differential.

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

• site_factsA
  4/5.0
  Behavior4/5

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

  The description discloses that the data is public and factual, that the scope is a single named site, and that metric fields are unit-suffixed — useful behavioral details beyond the schema. It does not cover errors, missing-site behavior, or access concerns, but for a simple public fact lookup, most important behavior is transparent enough.

  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 front-loaded sentence that packs the resource, the fact categories, and a format note without padding. Every phrase 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 one required parameter and no output schema, the description lists the main content categories effectively. It does not explicitly explain behavior for unknown site names or how a page link is returned, keeping it complete but not exhaustive.

  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 coverage is 100% and the only parameter 'site' is already described as 'Site name or slug', so the description adds little meaning beyond the schema. The mention of 'named dive site' is consistent but does not deepen the parameter semantics.

  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 the specific resource (one named dive site) and the concrete facts returned: depths, difficulty, shore/boat access, hazards, entry and exit notes, and a page link. This makes the tool clearly distinct from the sibling tools, which cover windows, timing, species, and regions.

  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?

  It establishes the use case: looking up static public facts for a single named dive site, which is different from the siblings' time-based or region-based queries. It does not explicitly say when to use it instead of an alternative, but the context is clear enough for moderate guidance.

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

• top_dive_regionsA
  4.1/5.0
  Behavior4/5

  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 conveys that the tool is forecast-oriented, time-limited to ~72 hours, and not a safety guarantee. It could expand on ranking logic or output shape, but the essential caveat is well covered.

  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?

  Two sentences, no redundant wording, and the main purpose is front-loaded. The safety caveat earns its place by clarifying the tool's limitations without bloating the description.

  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 zero-parameter read-only ranking tool, this is nearly complete: purpose, time horizon, and operational caveat are all stated. The lack of an explicit output-structure description is a minor gap, but an agent can still call and interpret the result confidently.

  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 zero parameters, so there are no input semantics to document. The description appropriately focuses on what the tool returns rather than filling a param gap, which is exactly right for a no-argument tool.

  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 description clearly states a specific resource (world regions), the action (ranked), and scope (favorable dive-forecast windows over ~72 hours). It implies a broad regional ranking that differs from siblings like find_dive_windows, but it does not explicitly name or distinguish sibling tools, so it stops just short of a 5.

  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?

  It provides clear context: use this for forecast planning, not as safety clearance, and always verify on-site conditions. This gives a strong sense of when and when-not to rely on it, though it stops short of naming alternative sibling tools for specific use cases.

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

• find_dive_windowsA
  4.4/5.0
  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 well. It calls out the forecast-planning-only limitation, the 'never a safety clearance' caveat, unit conventions, and the instruction to assess conditions on-site. This is specific, honest behavioral context beyond what the schema could convey.

  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 main purpose and output. It wastes little space, though 'always assess conditions at the water' somewhat restates the safety caveat established one sentence earlier. Overall, every major clause contributes context, but a slight redundancy keeps it from being perfectly clean.

  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 there is no output schema, the description compensates well by describing what results include: favorable and moderate windows, wave height, wind, timing, and site links. It also explains unit handling for US users and disclaiming safety, so the agent knows what to expect and how to frame output. Nothing critical is missing for the tool's intended purpose.

  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?

  The schema already describes day, near, and radius_km, so the description does not need to repeat those. It adds a little orientation through 'near {place} on {day}' and notes unit-suffixed fields such as wind_kn in knots, but it does not meaningfully explain lat/lng or otherwise compensate for the remaining schema coverage gap. This is acceptable but not exceptional.

  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 a specific verb-plus-resource: it finds ranked scuba-diving forecast windows near a place on a specific day. It also gives the exact user question it answers, including output categories (favorable and moderate windows) and site links, which makes it easy to distinguish from siblings like site_facts or top_dive_regions.

  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 communicates when to use the tool: when someone asks 'where can I dive near {place} on {day}?' and wants forecast planning information, not safety clearance. It does not explicitly name alternatives or say when not to use it, but the context is clear enough for an agent to route the request appropriately.

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