NIAR

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

With no annotations, the description carries the full burden and does real work: it discloses the 10-store cap, the ordering semantics with and without coordinates, the meaning of stores_total, and a caution not to affirm availability when availability_status is unknown. It omits what happens if the product is not found, whether all params are optional, and any pagination/limit control beyond the fixed 10.

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?

Front-loaded with the core purpose, then behavior, then the availability caveat; each sentence adds information. Slightly dense, and the final sentence reads as policy instruction rather than tool description, but nothing is wasted.

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 must convey return shape; it does partially by referencing stores, stores_total, and availability_status. However, it never states that all three inputs are optional or how the product is identified, leaving a meaningful gap for a detail-fetch tool.

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%, so the description must compensate. It explains lat/lon behavior well (proximity vs. arbitrary ordering), but niar_id — the identifier for "a specific product" — is never mentioned, leaving the most important parameter's role and format unexplained.

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 and resource ("Get details of a specific product and the stores that carry it"), which is clearly distinct from the sibling search/store tools. It never names a sibling explicitly, so the agent must infer that products-search-nearby is the search counterpart.

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?

Gives concrete when-to-use guidance: pass lat and lon for the 10 nearest stores, omit them to get 10 in no particular order, with "(recommended)" signaling the preferred path. It adds an operational rule for unknown availability, but offers no routing advice versus products-search-nearby or stores-get.

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?

No annotations exist, so the description carries the full burden, and it does disclose meaningful behavior: result ordering by usefulness (priced and in stock first), at most 3 products per store, unknown fields omitted, and an explicit caution not to affirm availability when the status is unknown or unreachable. It omits permission, rate-limit and latency characteristics, which keeps it short of a 5.

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 front-loaded with purpose and input form, then return shape, then recovery and safety advice, and every sentence carries actionable content. It is dense but not padded, though the availability caveat could be tightened.

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 and no annotations, the description still describes the return payload (price, availability, trust level, distance, ordered by usefulness) and the empty-result fallback. The only material gap for a six-parameter tool is the unexplained trust_level parameter.

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% across six parameters, so the description must compensate. It explains lat/lon vs place, query phrasing and the radius example value, but it never mentions trust_level or what values it accepts, leaving one parameter undocumented in both places.

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 specific verb and resource ('Search for products available in nearby physical stores in Spain'), which is distinct from the sibling retrieval tools products-get, stores-get and stores-search. An agent can tell that this is a geographic proximity product search without opening any schema.

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?

It gives concrete routing guidance for inputs ('Pass lat/lon, or a place name if you do not have coordinates') and a recovery strategy ('retry with a larger radius (e.g. 5000) or a more generic term'). It also advises Spanish queries for better recall. It never explicitly contrasts itself with products-get or stores-search, so the alternative-selection guidance is incomplete.

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?

With no annotations, the description carries the full disclosure burden and does well: it reveals the default result set (50 most recently updated), the upper bound on limit (100), and the meaning of the inventory_total return field. It omits any statement of permissions or that the operation is read-only beyond the verb 'Get'.

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, front-loaded with the core purpose, then the query/limit behavior, then the return-field note. Every sentence adds information and none repeats the name or schema.

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-parameter read tool with no output schema, this covers the essentials, including the meaning of a returned field. It stops short of describing what store 'details' are returned or what limit defaults to when query is absent, which an agent would want to know.

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, and it does for two of three parameters: query is explained with a concrete example and its fallback behavior, and limit is bounded at 100. store_id receives no explicit explanation and the limit default value is never stated, leaving a small 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?

The description uses a specific verb and resource ('Get details of a specific store and part of its inventory') and the phrase 'specific store' implicitly separates it from the sibling stores-search. It does not name any sibling explicitly, so an agent must infer the routing rather than being told it.

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?

It gives conditional guidance on parameter use ('pass query to search inside the store... without it you get the 50 most recently updated'), which is genuinely helpful. However, it never states when to choose this tool over stores-search or products-get, so alternative selection is left to inference.

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?

No annotations are supplied, so the description carries the full load. It does disclose a result cap (20 stores), the returned fields, and a genuine data quirk about missing street addresses, which is real value. It says nothing about pagination, ranking by distance, auth requirements, or behavior when multiple locators are given.

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, front-loaded with purpose and result shape, with the address caveat last. No wasted wording, though the final sentence about city and coordinates reads a bit terse and could be clearer.

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, and the description partly compensates by listing return fields and the result limit. However, for a six-parameter, zero-coverage schema it leaves too much unexplained: radius units, what query and category filter on, and the lat/lon vs. place contract.

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% across six parameters, yet the description only explains lat, lon, and place. The query, radius, and category parameters are entirely undocumented in both schema and description, so half the inputs are unexplained and the radius unit (meters vs km) is unknown.

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 and resource ("Search for physical stores") plus a geographic scope (Spain) and a proximity criterion (near a location). That is enough to separate it from stores-get, though the description never names the sibling or states the distinction explicitly.

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 by the phrase "near a location" and by the concrete hint to fall back on city plus coordinates when street addresses are missing. There is no explicit when-to-use vs. stores-get, and no rule for whether lat/lon or place takes precedence when both are supplied.

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