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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds value beyond that by disclosing the shape of each mode (counts per collection vs. paged file listing) and the pagination contract ('pass next as cursor'). It does not describe ordering or page size limits, which keeps it at 4.

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, front-loaded with what a collection is, then the two modes, then the cross-reference. Nothing is redundant. The elliptical grammar in the second sentence costs a little parsing effort but no space is wasted.

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 read tool with no output schema and safety already covered by annotations, the description supplies the essentials: both modes, the return content of each, and the cursor loop. Missing only minor details such as ordering, page size, and whether a workspace context is implicit.

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 both parameters, and it does explain the meaning of collectionId (switch to file-listing mode) and cursor (feed back the previous response's 'next' value). However it never clarifies that 'next' is returned as the cursor field, and it gives no type/format or empty-page behavior. Adequate but leaves real ambiguity at zero schema coverage.

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 definition names the resource (collections), defines it concretely as 'hand-picked sets of the workspace's files, beside folders', and describes the two result modes. The agent can distinguish this from folder listing and knows use_asset is the follow-up action. The telegraphic phrasing ('the collections with how many files each') makes the verb implicit rather than stated outright, which keeps it short of a 5.

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?

It gives explicit conditional guidance: omit collectionId to enumerate collections with per-collection file counts, supply it to page through that collection's files. It also names the next step (use_asset adds them to the project). It does not state when to prefer this over folder-oriented listing siblings, so it falls short of full when/when-not coverage.

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