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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial context beyond these: token authentication needs, a per-day cap on the enrich feature, fallback behavior if enrich fails ('if it fails you still get the un-enriched program'), and automatic conversion of GitHub blob URLs. This goes well beyond the annotation hints and gives the agent a clear behavioral model.

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 lengthy but every sentence carries necessary information: purpose, sources, actions, auth, enrich behavior, and post-import step. It is front-loaded with the purpose and then systematically covers each aspect. It could potentially be condensed, but given the complexity (6 parameters, multiple sources, and modes), the verbosity is justified. No filler or redundancy.

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 tool with six parameters, seven sources, three actions, and a special enrich mode, the description covers all necessary operational details: source-specific constraints, token prerequisites, per-day limits, failure fallback, and a recommended follow-up tool. There is no output schema, but the description clarifies that a program is returned and suggests visualize_schedule. The agent has everything needed to invoke 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?

Though the schema covers 67% of parameters with descriptions, the description adds significant meaning to all six: it explains the source enum values (spoonacular, themealdb, protocolsio, cooklang, opentrons, benchling, llm-text) with usage notes, clarifies action semantics (search vs import vs random), explains token requirements per action, and details the enrich flag's behavior. This goes far beyond the bare enum and type definitions.

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 precise action ('Import a recipe or lab protocol from an external source into a Rhylthyme program') and enumerates specific sources and actions, distinguishing it from siblings like import_text (which handles text input) and search_public_recipes (which only searches). It is unambiguous about scope and behavior.

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?

Provides explicit guidance: lists preferred vs fallback sources, specifies when token is required vs not, explains action-specific requirements (e.g., cooklang and opentrons require action='import'), and directs the agent to run the returned program through **visualize_schedule** after import. It also details the enrich option and its conditions, leaving no ambiguity about when to use this tool versus alternatives.

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