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

The description discloses important non-obvious behavior beyond the annotations: membership fields 'route to the regular-collection endpoint, which 404s for a smart collection', link_uuids is a 'full replace', and image_upload_id can be null to remove the cover. This goes well beyond the readOnly/destructive/idempotent hints, though it doesn't cover every edge case like invalid values or auth.

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 dense but every clause carries load-bearing detail: the full field list, the smart-collection exception, the null-to-remove behavior, and the verification step. There is no filler or repetition of schema fields, and the most important distinctions are front-loaded.

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 high-complexity tool with 11 parameters, no output schema, and no enum constraints, the description addresses the most error-prone behaviors and provides a follow-up verification step. It is incomplete only on a few less risky fields like layout and visible_on_splitpage, but the core collection-update semantics are sufficiently covered.

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?

With only 55% schema coverage, the description compensates for the riskiest parameters: it clarifies image_upload_id null semantics, section patchability, and the meaning and constraints of links_to_add/links_to_remove/link_uuids. However, it does not add semantics for query, layout, visible_on_splitpage, or name, which remain underspecified by both schema and description.

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, non-tautological purpose: it enumerates exactly what can be updated on a collection ('name, visibility, cover image, owning section, or membership'). It further distinguishes regular from smart collections, which anchors the tool's scope and separates it from sibling update/set tools.

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 gives clear conditional guidance: membership fields are for 'REGULAR collections only', smart collections can't use them because 'its membership is its query', and it tells the agent to 'verify with split_get_collection_links' after membership changes. It does not explicitly name alternatives like split_set_collection_image for cover images, but the regular-vs-smart distinction is strong enough for most routing.

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