Import from an external source

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real context beyond them: account prerequisites for import/random/benchling, the parallel-track behavior of enrich, and a daily model-call cap. That rate-limit and auth detail is the kind of thing annotations cannot express.

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?

Purpose is front-loaded and the remaining lines are dense, telegraphic clauses that each carry information (sources, actions, auth, enrich). No filler, though the clipped phrasing occasionally forces re-reading.

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 tool with no output schema, it covers sources, actions, account requirements, enrich semantics, and states the return value ("Returns the program"). Minor gaps remain around the text-paste path and how it relates to the import_text/load_program siblings.

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 description meaningfully supplements the schema by mapping each source to its domain, defining what query means per action, and explaining enrich's parallel-track behavior. The token parameter's usage (omit when connected) is left mostly to the schema, keeping it below a 5.

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?

Opens with a specific verb and resource set ("Import a recipe, protocol or run of show into a program") and then enumerates the valid sources grouped by domain. It does not explicitly distinguish itself from close siblings like import_text, load_program, or load_public_recipe, so a 4 rather than a 5.

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?

Gives concrete conditional guidance per action (search needs no account, import takes a URL or id, random) and names which paths require the Rhylthyme account. It stops short of naming sibling alternatives for each case, so it is clear context without explicit exclusions.

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