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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context the annotations lack: which actions require the user's Rhylthyme account, and that enrich kicks off parallel tracks consuming one model call capped per day. It is silent on error/partial-import behavior, but the incremental value over annotations is real.

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?

Dense and front-loaded: the core purpose leads, then source taxonomy, then action semantics, then auth and enrich. The telegraphic fragment style ('action: search (no account needed), import ...') is compressed but readable, and no sentence is filler.

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 6-parameter, no-output-schema tool, the description covers purpose, source/action enums, auth prerequisites, and the enrich modifier, and notes the return ('Returns the program'). Remaining omissions (text parameter interplay, token handling) are covered by schema descriptions.

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?

At 67% schema coverage the schema does much of the work, but the description adds meaning beyond it: it groups the source enum values into recipes/lab/cooklang and ties query to the action ('query = URL or id'). text and token are left to the schema descriptions, and the description omits that action='import' can also draw from pasted 'text', a minor gap.

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 and resource with scope: 'Import a recipe or protocol from a URL or service into a program,' and enumerates the external sources grouped by domain (recipes vs lab). It does not, however, distinguish itself from the sibling import_text (pasted-text path) or load_program, so the agent must infer the boundary.

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 spells out the three action modes and their conditions — search needs no account, import takes a URL or id, random is a discovery path — plus the account requirement for import/random/benchling. That is concrete when-to-use guidance for the tool's own modes, but it gives no guidance on choosing this tool over siblings such as import_text or search_public_recipes.

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