Read a recipe

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint: false, so the safety profile is covered. The description adds meaningful behavioral disclosure: subscription recipes omit ingredients and steps, the site maintains dual metric/US renditions, and the servings parameter triggers server-side recomputation that is not published by the site. No contradiction exists.

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 what the tool does, and each remaining sentence carries a distinct behavioral fact: id source, subscription behavior, and the dual-rendition rationale for unit_system. There is no filler or repetition of schema fields.

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?

Given the output schema exists, the description does not need to explain return values. It covers all important calling context: where to obtain id, how subscription recipes behave, how unit_system works, and how servings scaling is handled. The tool is fully specified 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 coverage is 100%, but the description goes beyond the schema by explaining that id is the page's own path, that servings quantities are recomputed by this server and labeled under 'scaling', and that unit_system selects one of the site's own words rather than a conversion. This gives the agent semantic understanding that the schema alone does not fully convey.

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 and resource: 'Read one recipe on BBC Good Food' and enumerates exactly what is returned (ingredients, steps, times, rating, nutrition). It implicitly distinguishes itself from search_recipes by telling the caller to pass an id that a search_recipes row carries, making the tool's role as a single-item reader unambiguous.

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 concrete guidance on where the id comes from ('a search_recipes row carries') and how unit_system should be chosen between the site's two renditions. It also tells the user what to expect for subscription recipes and directs them to the site page. It does not explicitly contrast with list_filters or scale_ingredients, but the usage context is clearly implied.

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