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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false. The description contributes real value beyond them by disclosing deduplication semantics ('keeps each record once with its sources'), which implies source records are preserved rather than moved. It does not say whether the merged collection is new or one of the inputs is reused, nor whether the operation is atomic or reversible.

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?

One tight sentence with no filler, and the merge outcome is front-loaded. However, the brevity here is under-specification rather than economy: the sentence has room to state the parameter roles and the ownership/limit constraints without becoming verbose.

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?

This is a mutating, multi-input operation with no output schema and no parameter documentation, so the description is the only place an agent could learn the return shape or side effects. It gives none of that, and 2-20 collection bounds, project scoping, and idempotency are all left to inference.

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?

With 0% schema description coverage across four parameters, the description must carry the burden and largely does not. It never explains that collection_ids selects the sources (2-20 of them), that name is the merged collection's name, or that request_id is an idempotency key with a strict format. Only the ownership constraint on the source collections is conveyed.

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 states a specific verb and resource: 'Merges collections the caller owns into one', and adds the dedup outcome ('keeps each record once with its sources'). That distinguishes it from siblings like filter_collection, share_collection, and get_collection. It stops short of naming an alternative or stating what the result is.

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?

There is no guidance on when to use this instead of filter_collection or share_collection, and no prerequisites are spelled out beyond the implicit 'caller owns'. Constraints baked into the schema (2-20 collections, required request_id) are never surfaced as conditions for use.

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