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

The annotations already declare destructiveHint=true and idempotentHint=true, so the description doesn't need to repeat that. It instead adds non-obvious blast-radius context: the works remain on the platform, only the collection membership is affected, and the collection object survives. It does not say what happens when a supplied work is not in the collection (silent no-op vs. error), which is the one behavioral detail still missing.

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?

Three short sentences, each carrying a distinct payload: what it does, when to do it, and what is not destroyed. The scope constraint leads, and nothing is redundant padding.

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 two-parameter mutation with full schema coverage, annotations covering safety and idempotency, and no output schema to explain, the description covers intent, gating, and destructive scope adequately. The only shortfall is undefined partial-failure behavior when a listed work is absent from the collection.

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 parameters are richly documented in-schema (accepted URI/slug forms, the 1–20 bound, the collections field cross-reference). The description's "up to 20 works" and "naming the works" restate schema constraints rather than adding new semantics, so baseline 3 applies.

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?

"Take up to 20 works out of one of the signed-in member's collections" gives a concrete verb, resource, scope cap, and ownership qualifier, and the closing clause ("the collection itself is never deleted") preempts confusion with collection-level deletion tools. An agent can distinguish this from add_to_collection or create_collection without opening any schema.

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?

"Only when the person clearly asks for it, naming the works" is a genuine, actionable gating condition that also specifies the required input form. The only gap is that no alternative tool is named for the adjacent intents (adding, or deleting a whole collection), so the agent must infer them from sibling names.

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