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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, and the description's 'a work already there is left as it is' largely restates the idempotency hint. What it genuinely adds beyond annotations is positional behavior ('at its top, as on the site') and the fact that the target must belong to the signed-in member. It says nothing about what happens on partial failure or what the response contains.

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 ordered by importance: what it does and where items land, then the permission-style constraint, then the duplicate behavior. No filler and nothing buried.

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 and annotations covering the safety profile, the description supplies the remaining non-obvious context: ordering, duplicate handling, and the requirement that the collection be the member's own. The only real gap is the lack of any statement about the response or partial-success behavior, which matters since there is no output schema.

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%, including accepted identifier formats for both collection and works, so the schema carries the parameter burden. The description's 'up to 20 works' merely echoes maxItems and adds no format or syntax detail beyond the schema.

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 verb and resource ('add ... works ... to ... collections'), plus concrete scope limits (up to 20, placed at the top, signed-in member's collections). It does not name the obvious inverse sibling remove_from_collection, so an agent must infer the pairing, but the purpose itself is unambiguous.

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 asks for it' is an explicit usage restriction that prevents unsolicited writes, which is valuable for a mutation tool. It stops short of naming alternatives (e.g. create_collection when the collection does not yet exist), so the routing guidance is partial.

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