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

Annotations already declare read-only, idempotent, non-destructive, and closed-world, and the description still adds real value: it discloses the payload deliberately excludes source text and comment bodies, states that a headless account with no open tab returns items: [], and names the required scope (project:read). Those are exactly the behavioral facts an agent cannot infer from the annotations.

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 sentences, each carrying a distinct load: what is read and in what order, what is returned and what is withheld, and the empty-result plus scope caveat. It is front-loaded with the resource and has no filler.

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, the description compensates by enumerating the returned fields (anchors, comment-thread IDs, page IDs/names) and their boundaries (no source text or bodies). The zero-result case, authorization scope, and pagination path via schema are all covered, so nothing essential is missing for a two-parameter read tool.

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%, so limit (max 100, default 20) and cursor semantics are already fully documented in the schema. The description adds no parameter-level detail such as what ordering the limit slices or how the cursor interacts with ranking, so the baseline of 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?

States a specific verb and resource: reads authorized live or recent Bloom canvas tabs ranked by last focus, returning selection anchors, comment-thread IDs, and page IDs/names. The 'selection' resource is distinct from what any sibling (read_frame_state, list_canvas_frames, list_recent_canvas_changes) covers, though no sibling is named explicitly to sharpen the contrast.

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?

Gives clear usage context: 'Useful for user requests about selected objects or the current canvas.' This tells the agent when to reach for this tool versus the frame/page listing siblings. It stops short of explicit exclusions or named alternatives, which keeps it out of 5 territory.

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