Life Scientific product catalogue

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

Annotations already establish readOnly/idempotent/non-destructive, so the description is free to spend its words on the response payload, which it does by enumerating the regulatory facts returned. It also implies a negative outcome path with 'if so', though it never says what comes back when the product is not authorised in that market.

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, front-loaded with the core action, and the second sentence adds a distinct payoff (the intended question shape) rather than restating the first. Nothing is wasteful.

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, describing the returned fields is exactly the right compensation, and annotations cover the safety profile. The main remaining hole is the not-authorised case, which matters for interpreting a question phrased as a yes/no.

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%, including the locale enum and the ISO alpha-2 guidance for region, so the schema already carries the parameter burden. The description only adds the informal 'country Y' framing around region; it says nothing about locale or its fallback that isn't already in 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?

States a specific verb and resource: 'Check whether a product is authorised in a specific market/region'. The returned fields (registration status, number, pack sizes, approved uses) sharpen the distinction from get_product, but no sibling is named explicitly, so an agent must infer the boundary rather than being told.

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?

Supplies a concrete usage scenario in natural language: 'can I use product X in country Y?'. That is a clear positive trigger, but there is no statement of when NOT to use it (e.g. for general product data, use get_product) and no mention of prerequisites such as needing a known slug vs. searching first.

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 the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower. The description still adds useful behavioural context by describing what is returned per market — registrations, approved crop/target uses, PHI, pack sizes, safety summary — which is the main thing an agent needs to know before calling a detail endpoint with no 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?

One front-loaded sentence with no filler; the identifying parameter and the returned content are both stated immediately and every clause carries information.

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 correctly spends its words enumerating return contents, which is exactly the gap that needed filling. It stops short of covering locale effects on the response or error behaviour, but the schema handles locale semantics adequately.

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%, with slug documented as coming from search_products and locale documented including the important rule that regulatory facts are never translated. The description itself adds only 'by its slug', so the schema is doing the heavy lifting — baseline 3.

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 the full detail for one product', keyed by slug, and enumerates the payload (active ingredients with FRAC/HRAC/IRAC codes, formulation, uses, per-market registrations). This clearly separates it from the list-style search_products sibling, though no sibling is named 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 rather than stated: 'by its slug' plus the schema note '(from search_products)' signals the search-then-fetch flow. There is no explicit when-not guidance, no mention of when to prefer get_product_documents, and no note on behaviour for unknown slugs.

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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: documents are 'current' per registered market, include download URLs and version identifiers, and are market-partitioned, which warns the agent that a single call without region may span markets.

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, front-loaded with the core action and return contents, followed by the one operational caveat that matters. No filler or restatement of the title.

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 two-parameter read-only tool with no output schema, the description adequately covers what is returned (label, SDS, URLs, versions) and the market-partitioning caveat. Minor gap: it doesn't say explicitly what happens when region is omitted, though 'per registered market' implies a multi-market result.

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 real meaning: it explains why market/region selection matters (regulatory labels differ per market) rather than just restating the field. The slug's origin from search_products is repeated from the schema, which is the only wasted overlap.

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 the current regulatory documents for a product') and enumerates the artifacts returned: official product label, SDS, download URLs, and versions. It is clearly distinguishable from the sibling get_product, which presumably returns product data rather than regulatory documents.

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 clear conditional guidance: labels are market-specific and the caller must use the document for the market where the product will be applied, which implicitly motivates the optional region parameter. It also points at search_products for the slug. It stops short of explicit when-not guidance or naming get_product as the alternative for non-document data.

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 readOnly, idempotent, non-destructive, closed-world behaviour, so the safety profile is covered. The description adds materially beyond that: it discloses a data-coverage limitation (targets not recorded for every market), prescribes the recovery strategy, and warns not to conclude absence of products. It does not explain result ordering or how limit interacts with total matches, 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?

Purpose and filter scope are front-loaded in the first sentence, usage example second, and the fallback caveat last. Every sentence carries actionable information with no filler, despite the description being longer than average.

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 seven optional parameters, no required fields, and no output schema, the description supplies exactly what is missing: what the return is ("a compact list of matching products"), how to combine filters, and how to behave when coverage gaps produce empty results. Nothing an agent needs in order to call it correctly is absent.

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 every parameter including query word-AND semantics and locale defaults is already documented in structured data. The description adds only the conceptual framing that filters combine with "and/or", which is useful but not meaningfully beyond the schema baseline.

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?

Opens with a specific verb and resource ("Search the Life Scientific crop-protection catalogue") and enumerates the exact filter dimensions. It is clearly distinguishable from siblings get_product and get_product_documents, which retrieve single records and label documents rather than listing matches.

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 an explicit use case ("problem-first questions like 'what controls septoria in wheat in Ireland?'") and a concrete fallback when a target search returns nothing: re-search by crop and type, then point the user to get_product_documents. It also names the sibling to use for label confirmation, so the routing decision is fully determined.

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