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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description does add one real behavioral trait not in the structured fields: the result shape changes depending on which parameter is supplied (collections vs. frames). The POST/endpoint note is transport trivia rather than behavior, and nothing is said about result size or pagination.

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 resource definition and followed immediately by the parameter-driven branch. The trailing 'POST /v3/list_collections' endpoint is not useful for tool selection and slightly dilutes the otherwise tight phrasing.

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 0 required params, 100% schema coverage and no output schema, the main thing an agent needs is to know the response depends on inputs — which the description covers. Missing only secondary details like pagination or how to discover valid collection ids, which are minor for a read-only listing tool.

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 description coverage is 100% and both parameter descriptions already state the exact same semantics ('Required to list the frames inside a collection', 'compatible with this product code'), so the prose largely restates the schema. Baseline 3 applies; no format hints or valid-id discovery guidance are added.

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 the resource ('Frame collections (categories)') and, importantly, a second verb mode: listing frames inside a collection. This is more specific than a bare list tool and distinguishes it from siblings like list_mats or list_glazing, though it never names an alternative tool explicitly.

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?

'Pass a collection id to list the frames in it; pass a product code to show only collections and frames compatible with that print product' gives concrete conditional usage for each parameter, which is genuinely actionable routing. It stops short of stating when NOT to use it or pointing at get_frame for single-frame lookups.

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