Create Recipe Draft

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

Annotations already indicate idempotent, open-world, non-destructive, and read-write behavior. The description adds valuable context: encryption, validation of version and size, and the immutable link carrying influence through publication. No contradiction with annotations.

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 a single dense paragraph that front-loads the core purpose and then addresses usage scenarios. Each sentence adds value, though the density makes it somewhat packed. It is appropriately sized for the tool's complexity.

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 complex tool with a nested schema and five parameters, the description covers the main usage paths, idempotency behavior, and validation. The existence of an output schema (not provided) likely covers return values, so missing return details are acceptable. It could be more explicit about study_id semantics but is largely complete.

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 only 20%, so the description must compensate. It explains draft_id (reuse for idempotency) and source_revision_id (for copying published recipes), but leaves study_id and name without additional meaning. The nested snapshot fields are partially described within the schema itself.

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 ('Save') and resource ('an encrypted authoring draft') and explicitly distinguishes it from publishing, fitting, or consuming an attempt. It also clarifies the tool's role relative to siblings like publish_recipe_draft and update_recipe_draft by describing creation scenarios.

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 scenarios: starting from get_recipe_draft_template for new drafts, preserving the snapshot from get_recipe_draft when editing, and supplying source_revision_id when copying a published recipe. It also mentions reusing draft_id for idempotent retries. It does not explicitly contrast with update_recipe_draft, but the create/update distinction is implied.

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