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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: name collisions reuse the existing collection rather than erroring, and 'files stay where they live' confirms membership changes never move or copy assets. It does not disclose what is returned, how invalid assetIds are handled, or the 80/200 limits' consequences (those live only in the 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 tight clauses plus a clarifying sentence, with the modes front-loaded in the order an agent would need to consider them. Every phrase earns its place, including the trailing sentence that preempts a common misconception about file movement.

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 mutating, four-parameter tool with no output schema and no schema descriptions, the definition covers the mode space and the non-destructive semantics well. It is still thin on outcomes: no indication of what the response contains (e.g. the collection record) and no mention of failure modes for bad names or invalid asset IDs, which an agent needs to handle retries sensibly.

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 0%, so the description must carry the load, and it does: it maps name to collection naming/upsert, collectionId+name to rename, and addAssetIds/removeAssetIds to membership by assetId. That covers all four parameters with meaning rather than restating types. It does not clarify whether name is required for creation or what happens when name is supplied alongside addAssetIds.

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 (collection) and enumerates three distinct modes: create-or-reuse by name, rename via collectionId+name, and add/remove assets by assetId. The parenthetical 'or use the one with that name' pins down the upsert semantics precisely. It stops short of distinguishing this from sibling save_* tools or delete_collection, so it is clear but not sibling-differentiated.

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 expressed as parameter-driven mode selection: a bare name creates or reuses, collectionId+name renames, and addAssetIds/removeAssetIds mutate membership. That gives an agent enough to pick the right call shape without opening the schema. There are no explicit exclusions or when-not conditions, and the case of passing name together with addAssetIds is left unaddressed.

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