card_builder_build_from_recipe

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

No annotations are provided, so the description must convey behavioral traits. It explains that the tool returns a dict and suggests a follow-up validation step, hinting it is likely read-only and transform-only. However, it does not disclose potential side effects (e.g., does it check schema or modify anything?), permissions needed, or error conditions. The level of disclosure is adequate but not comprehensive.

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 efficient: it states purpose in one line, then provides a well-structured recipe example with clear comments, and ends with a brief output note. However, the example is somewhat lengthy and could be condensed or placed in a code block. Nevertheless, every sentence adds value, and the key info is 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?

Given the tool has only one parameter, an output schema (not needed in description), and the description thoroughly documents the parameter shape and output usage, it is reasonably complete. It covers what the tool produces and how to use the result. It lacks information on error handling or edge cases, but for a transformation tool this is sufficient.

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 input schema only defines 'recipe' as an object with no additional constraints (0% coverage). The description fully compensates by detailing the exact shape of the recipe, including all keys ('slots', 'root_slot', 'root_entity', 'blocks') with inline comments and types. This provides complete semantic meaning beyond the schema, enabling correct usage.

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 specifies that the tool 'Materialise a recipe shorthand into a full DocumentData (config) dict'. This verb+resource combination is precise, and the context distinguishes it from siblings like 'create_card' (which takes the config) and 'validate_config' (which checks it). The recipe shape is provided, making the tool's function unmistakable.

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 usage by showing the output should be passed to 'create_card' and suggests running 'validate_config' first. However, it does not explicitly state when to use this tool versus alternatives (e.g., directly constructing a config, using a template, or consulting a recipe guide). No exclusion criteria or contrast with siblings is given.

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