List Collections

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds that results include the recipes inside each collection and that output is paginated, which is meaningful for an agent planning payload size and follow-up calls. The custom-versus-managed provenance split is also useful behavioral context beyond the annotations. It doesn't state page size or total-count behavior, but that is a minor gap given the output schema.

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 sentences, front-loaded with the verb and resource, then the scope qualifier, then the pagination caveat. Every clause carries information and nothing is repeated from the schema verbatim.

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?

An output schema exists, so return structure need not be described, and both parameters are fully documented in the schema. The description supplies the domain vocabulary an agent needs to choose a kind value and the pagination heads-up. Only the absence of explicit cross-tool routing keeps it from full completeness.

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?

Schema coverage is 100%, so the baseline would be 3; the description earns above that by defining the meaning of the enum values that the schema only labels — "custom" as the user's own collections and "managed" as followed Cookidoo collections. Pagination is echoed from the schema rather than expanded, so it does not add further value.

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 names a specific verb and resource ("List recipe collections") and clarifies the two result domains: the user's own "custom" collections and the Cookidoo collections they follow, "managed". It also notes the results carry their recipes. It stops short of naming any sibling tool, so the distinction from create_collection, follow_collection or list_custom_recipes must be inferred from the verb.

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?

Usage is implied: this is the read path for collections, and the description notes it covers both owned and followed collections, which implicitly makes a single call sufficient instead of two. There is no explicit when-to-use guidance, no mention of when to prefer add_to_collection or create_collection instead, and no note that the returned payload is heavier than a bare collection list.

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