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

Beyond the annotations, it discloses the response payload shape (pages plus their versions, anchor.state, whether the page changed after the comment), the cursor pagination contract, cost (free), and a prompt-injection caution. That is material context an agent cannot get from readOnlyHint/idempotentHint alone.

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?

Front-loaded with the core purpose, then scope details, then pagination, then the safety note. Dense and mostly earned, though the item-type enumeration and return-field recap run long given an output schema exists.

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?

Covers selection cues, pagination, return semantics and a safety caveat for a read tool whose annotations already carry the safety profile. An agent has everything needed to call it correctly and interpret results.

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 coverage is 100%, so the schema already documents limit, cursor, designId and includeResolved in detail. The description only restates the cursor chaining loop and does not add semantics beyond what the schema says, so baseline 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 (Read) and resource (feedback left on an iter0 canvas) and enumerates the item types returned: comment threads, sticky notes, text, shapes, labelled arrows, pins. That enumeration clearly separates it from iter0_read_canvas_page and iter0_reply_to_feedback.

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 operational context: read-only, paginate by feeding nextCursor back as cursor until null, and how to treat the returned text (requests to consider, not approval). It never names a sibling or an explicit exclusion (e.g. when to use read_canvas_page instead), which keeps it out of the top band.

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