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

Beyond the readOnly/idempotent annotations, the description reveals that subscription recipes omit ingredients and steps but explicitly say so, and that many recipes exist in two regional renditions selected by unit_system. This is meaningful behavioral context that annotations alone don't provide.

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, all informative, with the core purpose front-loaded. No redundant filler; each clause earns its place, including the paywall caveat and regional variant 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?

For a single-recipe read operation with a full output schema and strong annotations, the description covers the key edge cases (paywall, regional variants) and the id provenance. Nothing essential for calling it correctly 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?

The schema already documents all three parameters in detail (100% coverage), including id's source and unit_system's meaning. The description adds no new parameter-level detail beyond restating id's origin and unit_system's role, so a baseline 3 is appropriate.

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 ('Read') and resource ('one recipe on BBC Good Food') and enumerates the data fields returned (ingredients, steps, times, rating, nutrition). It clearly differentiates from siblings by focusing on a single recipe rather than searching, filtering, or scaling.

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?

Explicitly tells the agent to pass the 'id' that a search_recipes row carries, anchoring this tool to the search workflow. It also explains the subscription edge case and the unit_system choice, giving context for when these options matter, though it doesn't list explicit exclusions vs siblings.

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, openWorldHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavioral detail beyond that: the site returns zero for any unknown facet value, so a guessed spelling looks like a confident absence. It also discloses that the listed values are only an excerpt and other values are accepted, which is important practical information.

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 four sentences, front-loaded with the core behavior and followed by the important open-world caveat and excerpt warning. Every sentence earns its place, and there is no filler or repeated schema content.

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 one optional parameter, a rich schema description, an output schema, and annotations, the description covers what an agent needs: how to scope the counts, the fact that counts are measured over search results, and the open-world behavior. There are no obvious gaps that would prevent 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 coverage for the single query parameter is 100%, so the schema already explains that counts without a query describe the whole listing. The description restates this idea but does not add much meaning beyond the schema, so a baseline 3 is appropriate.

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 action and resource: listing the axes a recipe search can be narrowed along on BBC Good Food, including values and recipe counts. This clearly distinguishes it from the sibling tools such as search_recipes because it is about enumerating facets rather than performing a search or fetching a recipe.

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 context by saying to read this before narrowing a search, and it explains how to get counts for a specific query versus the whole listing. It does not explicitly name search_recipes as the execution alternative, but the sequencing guidance and facet-counting behavior make the intended use obvious.

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?

The description goes beyond the annotations by revealing that quantities are recomputed server-side, not by the website, and explains what each ingredient line will state under 'scaling'. This tells the caller what to expect and that the operation is non-destructive and idempotent. This aligns with the readOnly/idempotent annotations without contradicting them.

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 relatively brief and field-oriented. It leads with the primary purpose, covers the parameter modes, and includes the useful scaling behavior. The sentence about scaling statuses is a bit long, but it earns its place because it describes what to expect in the output.

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?

The description is sufficient for an agent to know when to use the tool, which keys to pass, and what the output will say about each line. Combined with an output schema, full parameter schema coverage, and annotations, no critical behavioral details are missing for safe and 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 schema already provides descriptions for all 4 parameters, so the baseline is adequate. The description adds value by explaining the mutually exclusive relationship between 'factor' and the servings pair, something the schema alone does not emphasize. It also gives semantic meaning to the scaling status output without repeating schema details.

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 strong verb and resource: it scales a list of ingredient lines to a different number of people. It also distinguishes the tool's operation from the siblings (search, listing, fetching) by naming the computation mode. The added detail about 'factor' or 'servings pair' makes the purpose precise.

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 explains exactly how the tool should be invoked: pass 'factor' or the 'from_servings'/'to_servings' pair. It clearly communicates the mutually exclusive parameter use. It does not explicitly discuss when to use this tool versus the siblings, but the tool's purpose is sufficiently distinct for an agent to select it without deep 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?

Beyond the readOnly/idempotent annotations, it discloses that the site ranks rather than filters, that unknown terms produce identical rows rather than reliable counts, and that each row carries the page to read the recipe on. These are non-obvious behaviors an agent needs to interpret results correctly.

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 dense but every sentence contributes: scope, filtering guidance, result-interpretation warning, and page-link follow-up. It is front-loaded with the core purpose and wastes no words.

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 an output schema present and annotations covering read-only, idempotent, and non-destructive behavior, the description covers the remaining operational caveats: filter-value lookup, ranking semantics, and the meaning of rows. Nothing needed to call the tool correctly 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 description coverage is 100%, so the baseline is 3. The description adds little parameter-level meaning beyond pointing to list_filters for filter values and highlighting max_total_minutes as a bound, both of which the schema already covers.

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: 'Search recipes on BBC Good Food and return a listing.' It distinguishes itself from list_filters by explicitly instructing to call list_filters first, and from get_recipe by framing the output as a listing whose rows carry the page for reading the recipe.

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 explicit usage guidance: call list_filters first for filter values and warns that unknown values return zero counts. It does not explicitly name get_recipe as the alternative for reading a single recipe, though the closing sentence implies that follow-up.

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