Diver Atlas

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the useful scope caveat that this is a quizzing aid and returns no centre recommendation, which pre-empts a misuse. It says nothing about what a suitability result looks like or how conflicting inputs (e.g. deep_specialty) are weighed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two very short sentences with no filler; the scope limit ('does not recommend a centre') is placed second where it reads as a guardrail. Slightly clipped to the point that the first sentence lacks an explicit verb, which costs a point.

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

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 is the only place to learn what 'suitability' returns, and it does not say. For a five-parameter read-only computation tool with zero schema descriptions and no output contract, an explanation of the result shape would materially help, though the core inputs and purpose are covered.

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

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. It does convey the key semantic that all slugs share one cert and dive count, which is genuinely additive. But it leaves deep_specialty and last_dive_months completely unaddressed, and the array size limit and enum values are left to the schema.

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

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

The description names the resource ('Andaman slugs') and the operation ('suitability'), and the word 'multiple' plus the 'batch_' prefix implicitly distinguish it from the single-slug sibling check_suitability. It stops short of a clean verb+resource statement (it opens with a noun phrase 'Suitability for...'), so the sibling contrast is inferred rather than stated.

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

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

'Quiz helper' gives a usage context you would not otherwise infer, and 'does not recommend a centre' sets a clear negative boundary against list_centres and similar tools. It never explicitly routes to check_suitability for a single slug, so the caller has to infer the batch-vs-single split from the name alone.

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

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

Annotations already declare readOnlyHint and closed-world, and the description adds real value on top: it enumerates the return payload (status, reasons, verification, sources, canonical URL) despite having no output schema, and states an explicit non-behavior boundary.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Three short sentences with zero padding; the purpose and mechanism are front-loaded, followed by return shape and the scoping exclusion.

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

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

For a six-parameter rule-evaluation tool the return composition and boundary are covered, but the complete absence of parameter meaning leaves a material gap that matters for correct invocation.

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

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

Schema description coverage is 0% and six parameters (cert, dives, site, slug, deep_specialty, last_dive_months) carry no documentation. The description never names or explains any input, so an agent must infer that cert and dive history feed the rules.

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

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

States a concrete verb ('check') and resource ('suitability for one plate') plus the rule-based mechanism, and the return contents. It doesn't explicitly name batch_check_suitability as the alternative, so sibling differentiation is only implied by 'one plate'.

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

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

Usage is implied — evaluate a single plate's suitability — and the boundary 'does not recommend a centre' tells the agent what this tool won't do. However, there is no explicit when-to-use or when-to-prefer-batch_check_suitability guidance.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds nothing behavioral beyond a content listing — no indication of whether results are scoped per country, how the verification breakdown is structured, or whether hub URLs are always present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single short sentence with no filler, and the most distinctive element (coverage plus verification breakdown) is front-loaded. It is efficient, though efficiency here partly reflects under-specification rather than tight editing.

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

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

For a read-only overview tool with no output schema and an entirely undocumented optional parameter, the description should explain the country filter semantics and what an unscoped call returns. Neither is present, so an agent cannot call it confidently.

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

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

There is one parameter, country, with 0% schema description coverage and no required flag, yet the description never mentions it. The description therefore fails to compensate for the coverage gap: an agent cannot tell whether country is an ISO code, a name, or what omitting it returns.

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

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

The description names the returned content (country/area coverage, verification breakdown, hub URLs) but has no verb and never states that it retrieves an overview report. An agent can infer the resource from the name plus the noun list, but it gets no scope boundary versus siblings like list_centres or get_latest_conditions.

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

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

There is no when-to-use guidance, no mention of when to prefer this over sibling coverage/lookup tools, and no note that the country parameter is optional. The agent must guess the invocation context entirely.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that results are aggregate 'counts and breakdowns' rather than raw records, which is genuinely useful, but says nothing about shape, units, or coverage limits of that aggregation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single short sentence with the scope front-loaded and no filler. It is efficient, though the brevity comes partly at the cost of clarifying the undefined 'own plate data' term.

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

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

With no output schema, the description is the only place an agent can learn what comes back, and 'counts and breakdowns' does not specify structure, dimensions, or whether results are per-site or totals. For a read-only aggregate endpoint this is too thin to call confidently.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The schema is fully empty and consistent with a no-argument aggregate call.

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

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

The description names a resource and a scope (dive-site counts and breakdowns for Andaman), which is more than the opaque tool name gives. However, 'get_data_study' suggests a broader study object than what's described, and the phrase 'own plate data' is undefined jargon an agent cannot resolve from this text alone.

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

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

There is no indication of when to call this versus siblings like get_site_plate, get_atlas_overview, or get_latest_conditions, even though get_site_plate sounds closely related. The agent is left to guess whether this is an aggregate report, a raw dataset, or a per-site lookup.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description adds almost nothing behavioral beyond the word "summary" – it does not say what the summary omits relative to the full guide, nor what happens when the slug is unknown (empty result vs. error).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Six words with zero padding and the key qualifier ("by slug") front-loaded. Brevity is not the problem; being underspecified rather than efficient is why it lands at the middle of the scale.

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

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

For a low-complexity single-parameter read tool with annotations and no output schema, the bar is modest, but the description still leaves the slug format and the notion of "summary" undefined. An agent can guess how to call it, but not confidently what it will receive.

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

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

The single parameter has 0% schema description coverage, so the description carries the full burden, and "by slug" only tells the agent that the value identifies a guide. It gives no format, source (where slugs come from), or case/URL-safety expectations.

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

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

"One guide summary by slug" implies a single-resource fetch keyed by slug and the word "summary" hints at a reduced representation. It does not use a verb and never explicitly contrasts with search_guides or get_data_study, so the agent must infer that this is the direct-lookup sibling of the search tool.

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

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

"By slug" implies you need a slug, but there is no statement of when to use this versus search_guides, nor what to do if you only have a name or ID. No prerequisites, no fallback guidance.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful context beyond annotations by disclosing that diver names, emails, and user IDs are omitted and that verification is included, but it does not explain ordering, recency semantics, default limit behavior, or what 'verification' entails.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is three short, front-loaded sentences with little waste. The purpose is stated first, followed by privacy and verification notes, though 'Includes verification' is vague enough that it slightly weakens the otherwise efficient structure.

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

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

For a simple read-only retrieval tool with no output schema, the description covers purpose and some data-handling context. However, it leaves meaningful gaps around the meaning of 'latest', how the limit parameter behaves, and what the returned condition reports contain beyond verification.

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

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 two undocumented parameters. It does not mention the required slug or the optional limit parameter, nor does it explain acceptable slug format or how limit controls result count.

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

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

The description states a specific resource and return type: timestamped condition reports for a plate. It is clear enough to distinguish this from sibling suitability or site tools, though it does not explicitly name or contrast with any alternative.

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

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

There is no explicit guidance on when to use this tool versus alternatives like check_suitability or get_site_plate. The description implies it retrieves latest conditions, but gives no conditions for use or exclusions.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the document is "public" and covers "v1", which is modest extra context, but says nothing about the document's size, format (JSON/YAML), or whether it is static.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single tight sentence with the key qualifier ("public") front-loaded and no filler. Every word earns its place.

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

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

For a zero-parameter retrieval tool with no output schema, the description tells the agent what is returned (an OpenAPI document) and its scope. Minor gaps like serialization format are unlikely to block correct invocation.

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

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

The tool takes zero parameters, so there is nothing to document and the schema is trivially complete. Baseline 4 applies for a no-parameter tool.

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

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

States a specific verb ("Return") and resource ("public OpenAPI document") with qualifying scope ("read-only v1 API"). None of the siblings deal with API specs, so it is effectively distinguishable, though it stops short of explicitly contrasting with doc-oriented siblings like get_guide or get_atlas_overview.

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

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

Usage is only implied: an agent can infer this is for fetching the API specification, but the description offers no when/when-not guidance or named alternatives. With many sibling tools, a note on when to prefer this over get_guide would help.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful content context (verification, sources, canonical URL) that partly substitutes for the missing output schema, but says nothing about behavior on unknown slug/site, error cases, or whether all fields are always present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single compact sentence with the return contents front-loaded. No filler, though it is too short for what it needs to carry.

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

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

With 0% schema coverage, no output schema, and a domain-specific term like "plate", the description should define the resource, both parameters, and expected failure modes. It leaves the meaning of "site", slug format, and the response shape entirely unaddressed.

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

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

Schema coverage is 0% for both parameters with no descriptions or enums. The description mentions "slug" in passing but never defines the format, and the required "site" parameter is never referenced at all, so it fails to compensate for the coverage gap.

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

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

States a getter for a "plate" keyed by slug, but "plate" is undefined jargon specific to this domain, so the agent can't tell whether it's a full record, a rendered document, or a status page. It is distinguishable from search_sites/list tools only by the word "Full", which is thin differentiation.

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

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

No statement of when to use this versus search_sites or get_species, and no prerequisites or exclusions. The only implicit cue is "Full", suggesting it's the detailed single-record fetch, but that must be inferred.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds only the cryptic phrase 'with matching site slugs from plates,' which does not explain what is returned or how the tool behaves beyond 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.

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

The description is a single sentence but is confusing and not front-loaded with a clear action. It is brief but underspecified rather than appropriately concise.

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

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

For a tool that retrieves a species by slug, the description fails to explain what information is returned, what 'slug' means, or what 'matching site slugs from plates' entails. With no output schema and no parameter detail, it is completely inadequate.

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

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

Schema description coverage is 0%, and the description does not explain what the required 'slug' parameter represents, its format, or how it is used. The input is completely undocumented.

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

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

The description says 'One species page with matching site slugs from plates,' which hints at retrieving a single species page but does not clearly state the action (e.g., 'Get a species by its slug'). It is ambiguous and does not distinguish from the sibling list_species.

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

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

There is no indication of when to use this tool versus alternatives, no prerequisites, and no exclusions. The description offers no usage context at all.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds one useful behavioral fact — the result set deliberately excludes phone, email, and ranking — but says nothing about filtering behavior, result volume, or pagination, so it adds little beyond 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.

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

It is short and front-loaded with the most important fact (what fields come back), but it is written as two clipped fragments rather than a sentence, so terseness comes at the cost of clarity rather than from it.

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

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

For a three-filter listing tool with no output schema and zero parameter documentation, the description should explain the filters and the shape of the list. It gives only a partial field inventory and an exclusion list, leaving the agent guessing about the core query mechanics.

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

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

Three parameters (area, country, locality) have 0% schema description coverage, and the description says nothing about any of them — not their format, whether they combine as AND filters, or whether they are exact-match or substring. With the schema carrying no documentation and the description not compensating, an agent cannot use these filters confidently.

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

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

The description is a noun fragment ('Public centre fields already shown on centre pages') that never states the action; the reader must infer 'lists centres' from the tool name alone. It conveys the field scope of the result but not the verb or resource, and does nothing to distinguish it from siblings like list_species or search_sites.

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

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

There is no statement of when to call this tool or which sibling to use instead. The only routing signal is negative scope ('No phone, email, or ranking'), which weakly implies 'use something else if you need contact data' but never names that alternative.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered. The description adds no behavioral context of its own — no ordering, no pagination behavior, no indication of what a result entry looks like or whether the list is exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

One short, front-loaded sentence with no filler. It is efficient, though the brevity comes at the cost of the missing parameter and usage information rather than because everything needed is present.

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

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

For a simple read-only list tool with no output schema, the description covers what is returned at a high level and annotations cover safety. However, it omits the only parameter's semantics and any notion of result size or pagination, which an agent needs to invoke it well.

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

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

The single parameter (limit) has 0% schema description coverage — even the maximum of 50 and the minimum of 1 are only machine-readable constraints. The description never mentions the limit parameter, its default, or its effect, leaving it entirely undocumented in prose.

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

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

States a specific verb (List) and resource (learn articles) and clarifies scope with the parenthetical 'certification explainers and FAQ pages'. Sibling tools like get_guide and search_guides appear to operate on different content, so the resource name alone largely differentiates, though no sibling is explicitly named as a contrast.

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

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

There is no guidance on when to call this versus search_guides or get_guide, no prerequisite conditions, and no exclusions. The agent must infer that this is the browse-everything counterpart to the search tool.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered by structured data. The description adds only a vague provenance caveat ("plate marine-life fields only") without explaining what that excludes from results or whether the list is exhaustive or paginated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

It is a single short sentence with no padding, so there is nothing to trim. However, the front-loaded content is an opaque noun phrase rather than a clear statement of what the tool does, so brevity comes at the cost of clarity.

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

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

For a simple read-only list tool with one optional parameter and no output schema, an agent still needs to know what a result item looks like and how many are returned. The description supplies none of that and does not compensate for the missing schema descriptions.

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

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

Schema description coverage is 0%, so the description must carry the meaning of the single `limit` parameter — but it never mentions it, gives no default, and does not explain that a maximum of 20 applies or what happens if omitted. The one parameter the tool has is left entirely to the raw schema bounds.

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

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

The fragment "Species where-to-see pages derived from plate marine-life fields only" names a resource but never states an action or what the tool returns (a list of species pages?). It is also indistinguishable in practice from the sibling get_species, which the description never acknowledges.

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

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

There is no when-to-use guidance at all — nothing says whether to call this versus get_species, list_centres, or list_learn_pages, nor whether paging/limits matter. The phrase "derived from plate marine-life fields only" hints at a data-scope restriction but is not framed as a selection criterion.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the useful constraint that only public guides are searched, but says nothing about result ordering, default limit, or return shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single front-loaded sentence with no filler and the scope ('public') placed early. It is efficient, though the brevity leaves gaps that other dimensions penalize.

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

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

For a simple two-param read-only search with no output schema, the description covers the core purpose but omits default limit/pagination behavior and the shape of returned items, which an agent needs to chain into get_guide.

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

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

Schema description coverage is 0% for both parameters. The description does clarify that 'q' matches title or description, but 'limit' (1-50, likely with a default) is left entirely unexplained in both schema and description.

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

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

States a specific verb (search) and resource (public island and topic guides) plus the matched fields (title or description), which clearly separates it from get_guide and search_sites. It does not explicitly name a sibling alternative, so it falls 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.

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

No when-to-use or when-not-to-use guidance is given, and the obvious alternative get_guide (fetch a specific guide) is never mentioned. The agent must infer that this is the discovery step before get_guide.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the read-only safety profile is covered. The description adds genuinely new context — that results carry a verification tier and a citable canonical URL — but says nothing about pagination, default limit, result ordering, or empty-result behavior for a 12-filter search.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two short sentences with no waste, and the core purpose is front-loaded before the return-value note. It is efficient, though it spends its second sentence on output rather than on the twelve filters that need explanation.

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

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

With 12 optional parameters, zero schema descriptions, and no output schema, the description leaves the agent guessing about what each filter accepts and how results are shaped. It covers citation/verification metadata but is inadequate for a multi-facet search tool of this complexity.

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

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

Schema description coverage is 0% across 12 parameters, and the description explains none of them: q, area, locality, country, type, entry, level, current, verification, limit, and the two depth bounds are all undocumented. The only relatable phrase, 'verification tier', refers to the return value, not to how the 'verification' filter works.

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

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

States a specific verb (search) and resource (dive-site summaries), which is enough to distinguish it from siblings like search_guides or list_species. It stops short of explicitly contrasting itself with those siblings, so it lands at 4 rather than 5.

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

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

There is no statement of when to use this tool versus search_guides, get_site_plate, or get_atlas_overview, and no prerequisites or exclusions. Usage is only inferable from the name and the word 'summaries'.

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