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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real value: scope is restricted to the signed-in member's own collection (an implicit auth/ownership constraint), works come back in the member's own order, and the default page size is 12 unless offset/limit extend it. It stops short of describing error behavior for a non-existent or inaccessible collection.

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?

A single dense sentence that front-loads the resource and scope, then the payload shape. Nothing is padded, though the nested colon-and-parenthetical structure takes a second read to parse.

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?

With no output schema, the description carries the full burden of describing the return payload, and it does so concretely (creator, caption, still, page per work). Gaps are minor but real: no mention of the 100-item limit cap, total-count/pagination terminus, or failure modes for an invalid collection identifier.

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 67%: offset and collection are documented in the schema, while limit has no description. The description partially compensates by implying a default page of 12 and that offset moves to 'the next ones', but it never mentions the limit parameter's name, its 1–100 range, or how ordering interacts with pagination. Baseline 3 is appropriate given the schema does most of the work.

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 resource ('one collection of the signed-in member') and its contents ('its works... each work with its creator, caption, a still and its page'), which is far more than the title repeats. It does not explicitly contrast itself with list_collections, so an agent must infer that this is the single-collection fetch while list_collections enumerates them.

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 rather than stated: fetch one collection and its works when you have identified a collection. It usefully tells the agent where to get the required `collection` value ('the « collection » field of list_collections'), which is a workflow hint. But there is no explicit when-not guidance versus list_collections or get_work, and no note on behavior when the collection is empty or unavailable.

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