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

Annotations already cover the non-destructive, read-only, idempotent, open-world behavior, so the bar is lower. The description adds behavioral value by stating the output shape (markdown summary plus live-timeline URL) and by telling the agent that a separate visualize_schedule call is unnecessary.

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?

Two front-loaded sentences with no filler. The first sentence states what loads and how it is identified; the second states the return value and the key workflow hint about avoiding visualize_schedule.

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-parameter tool with rich annotations and no output schema, the description covers the essential context: what it operates on, how to identify the recipe, what is returned, and the most important integration note. Nothing critical is missing for an agent to call it correctly.

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 fully documents the single parameter, including the type and provenance ('Program UUID (from search_public_recipes)'), so the description adds no meaningful parameter detail beyond 'by id'. Baseline 3 is appropriate because the schema carries the parameter semantics.

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 ('Load'), a resource class ('single public recipe / protocol / workout / event template'), and the lookup key ('by id'). The 'public' qualifier and return description distinguish it from siblings like load_program or load_run, and the input schema reinforces that the ID comes from search_public_recipes.

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 the intended workflow: after searching public recipes, load a single one by id. It explicitly tells the agent not to call visualize_schedule because the response already contains a live-timeline URL. However, it does not explicitly say when to prefer this over load_program or load_run.

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