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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that results are paginated and may include existing swipe-file items, which is useful scope context, but it says nothing about ordering, total counts, or what happens when a collection is empty or invalid.

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?

A single short sentence with no filler or repetition. It is front-loaded with the verb and resource, though the trailing 'including existing swipe-file items' clause is slightly cryptic without context.

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?

With no output schema and four undocumented parameters, an agent needs more than this to invoke confidently — particularly what shape the paginated payload takes and how to interpret the collection filter. Annotations cover the safety dimension, keeping it from being a 2, but the return/parameter story is thin.

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 parameter meaning, but it only gestures at pagination and collections. It never explains that 'workspace' is a required string identifier, that 'collection' is a UUID filter, or that 'limit' is capped at 24 and 'page' at 10000 — all left for the agent to infer from raw constraints.

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 read operation over 'collections and paginated saved research' and mentions swipe-file items, which gives a rough sense of the resource. However, it conflates two listable resources (collections vs. saved research items) without saying which the tool returns, and it does not distinguish itself from siblings like research_read, research_search, or references_ingest.

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 tool rather than research_search, research_read, or research_deep, all of which plausibly return related research content. A required 'workspace' parameter and optional collection filter are never framed as preconditions or use cases.

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