Nearwick business directory

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint, so the safety profile is covered. The description adds useful behavioral context beyond that by disclosing that results include external website data with a read date, dated checks, and whether the business manages the page. There is no contradiction 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.

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

The description is two sentences with no filler: the first sentence front-loads the full content scope, and the second sentence gives the exact input derivation pattern. The list of returned data is dense but every item maps to actual page content, so it 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?

With no output schema, the description carries the burden of explaining what the tool returns, and it does so thoroughly by enumerating business details, external website claims with read dates, dated checks, and management status. The input derivation and required parameters are also fully covered, making the definition complete for a simple read-only lookup.

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 100% and both parameters are individually described. The description adds meaning by showing the URL pattern /{country}/b/{slug} and clarifying that the slug comes from either the page address or search_businesses, giving the agent concrete provenance for both inputs rather than only their types.

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 clearly identifies a specific verb-resource: retrieving the full Nearwick business page for a country and slug. It enumerates the exact content included (location, website, opening hours, dated checks, management status) and distinguishes it from sibling search/list tools by targeting a specific page rather than finding businesses.

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?

The description gives clear operational context: use the country code and slug from the page address. It also indirectly points to search_businesses as the source of the slug via the schema. It does not explicitly contrast with alternatives or state when not to use it, so it stops short of a 5.

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, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful return-content detail but does not disclose additional behavioral traits such as pagination, ordering, or how the country code affects results. No contradiction with 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?

Two sentences with no filler. The first sentence packs the core output details, and the second gives a practical next step. Slight awkwardness in 'The kinds of business a country lists' but it is still efficient and front-loaded.

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 one-parameter, read-only tool, the description is complete: it explains what the response contains and how the output should be used. The schema covers the only input, annotations cover safety, and no output schema is needed given the descriptive output summary.

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 100%, and the single required parameter 'country' is fully documented in the schema with format and examples. The description adds nothing about the parameter itself, but the baseline of 3 applies because the schema already carries the semantic weight.

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 clearly identifies the resource (categories of business for a country) and the main output components (subcategories, counts, and top towns/regions). It is unambiguous and distinct from siblings like list_countries, though it is phrased as a noun phrase rather than an explicit verb like 'Lists...'.

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?

The description provides a clear downstream usage context: 'Use a category slug with search_businesses.' This tells an agent why they would call this tool. It does not explicitly contrast with list_countries or state when not to use it, but the intended workflow is clear.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond annotations by specifying that only countries with listed businesses are included, and that the response contains a count and a directory address. It does not mention ordering or pagination, but for a simple no-parameter listing these are minor omissions.

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 that front-loads the core purpose ('Every country with businesses listed on Nearwick') and immediately appends the two key output details. There is no filler, and every word contributes meaning.

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 carries the responsibility for explaining the return shape, and it does state the two main elements: business count and directory address. It does not specify sorting, pagination, or field names, which could matter for programmatic use, but for a simple directory list with no parameters the definition is reasonably complete.

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 has zero parameters, and the schema covers 100% of them trivially. Per the baseline rule, 0 params earns a 4. The description does not need to explain parameter semantics because there are none to explain.

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 uses a specific verb ('list') and resource ('countries'), and states exactly what is returned: every country with businesses on Nearwick, the business count per country, and the directory address. This clearly distinguishes it from sibling tools like get_business or search_businesses, which operate at the business or category level.

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?

The description implies this tool is for retrieving a country-level directory, but it does not explicitly state when to use it over siblings or when not to use it. An agent can infer its purpose from the phrasing, but there is no direct guidance such as 'for business details, use get_business' or 'for searching, use search_businesses.' This is adequate but not explicit.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real behavioral value beyond that: a 24-result page cap, the presence of a citable page address, and the two distinct default sort regimes. It omits total-count behavior and what happens when a page exceeds the documented maximum.

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 sentences, front-loaded with the search scope, then return shape, then sort behavior. No filler, though the sort sentence repeats detail already present in the schema's sort description and could be trimmed.

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 carries the return-shape burden and does so adequately: result page size, the per-item page address for citation, and pagination semantics. It is nearly complete for a nine-parameter search tool, missing only guidance on narrowing versus broadening results when a query returns nothing.

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 100%, so all nine parameters are already documented in the schema, including the 'has' filter, the country ISO code and the category slug source. The description's sort explanation largely restates the schema's own sort description, so it adds no meaning beyond structured data. Baseline 3 applies.

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 opens with a specific verb and resource plus scope: 'Search one country's listed businesses by words, category, town or region, and what the page carries.' That is far more than a restatement of the name. It stops short of a 5 because it never distinguishes this tool from the closest sibling, suggest_businesses, or explains when get_business would be preferred.

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 rather than stated: word searches default to best match and browsing without words defaults to A to Z, which hints that the tool serves both lookup and browse modes. There is no explicit when-to-use guidance, no exclusivity conditions, and no mention of the sibling tools that overlap (suggest_businesses, list_categories) beyond the incidental slug reference.

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 cover read-only, idempotent, non-destructive behaviour. The description adds meaningful behavioural context on top: it returns up to 8 ranked listings, includes per-listing reasons, exposes the full match search, and explains the fallback widening behaviour when nothing fully fits. This tells the agent what to expect without relying on an output schema.

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 dense sentences, each earning its place: purpose and examples, behaviour and output shape, and the edge-case narrative. The core action is front-loaded and there is no repetition of the schema or annotations.

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 fully carries the return-value burden and does so thoroughly: ranking, count, reasons, the widening fallback, and the relationship to the full search result. For a two-parameter read-only tool, nothing essential is missing.

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 100%, so the baseline is 3, but the description adds value by decomposing what the free-text request can encode: business kind, town/neighbourhood, days, and page content. This helps the agent construct a richer request than the schema's generic 'plain words' guidance alone.

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 verb ('Suggest') plus resource ('businesses for a request') and immediately gives concrete examples of input phrasing. It clearly distinguishes this from a plain search by promising 'up to 8 listings in order of fit' and the underlying 'search that shows every match', so an agent can tell it apart from siblings like search_businesses.

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?

The description makes the intended context clear: use when the user expresses a need in their own words, mentioning business type, location, days, and page requirements. It does not explicitly name sibling alternatives or state when not to use this tool, so it falls just short of full routing guidance.

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