Author and save a recipe

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

Annotations already indicate this is a non-read-only, non-destructive operation, but the description adds key behavioral context: 'does NOT change the live stream' and 'id/version/thumbnail are filled in automatically.' This informs the agent about side effects and auto-populated fields beyond what annotations convey.

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 long, but it is well-structured with a clear lead sentence, an explicit pointer to a field reference, and bullet-point breakdowns for background and sources. Every section serves a purpose and supports the complex nested parameter. It is appropriately sized for the complexity, though it could be slightly trimmed without losing essential guidance.

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 complex nested schema and lack of output schema, the description thoroughly explains the manifest structure, provides examples, and clarifies side-effect behavior. However, it does not describe any return values, error conditions, or validation behavior, which would help the agent understand the outcome beyond auto-filled fields.

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 only describes the 'manifest' parameter as 'The recipe manifest to author,' leaving nested fields undocumented. The description compensates with a full field reference, concrete examples for background and sources, and detailed Text source settings. This dramatically improves the agent's understanding of what the manifest should contain.

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: 'Author a new recipe from a manifest and save it to the user's recipe library.' It clearly distinguishes from the sibling apply_recipe by explicitly stating it does NOT change the live stream. This makes the tool's purpose unambiguous and differentiates it from the closest alternative.

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 explicitly names the alternative for live-stream changes: 'use apply_recipe for that.' It also clarifies the primary use case (saving a recipe without affecting the live stream) and gives guidance on constructing a minimal valid manifest. This goes beyond simple context and provides clear when-to-use and when-not-to-use guidance.

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