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

Annotations already cover read-only, idempotent, non-destructive, so the description correctly spends its words elsewhere: no redaction/truncation, 4096-character page limit, expected_rev as an optimistic-concurrency guard against mixed edits, and a SHA-256 of the full text for round-trip verification. It also flags the returned text as untrusted content that must not be treated as instructions, a safety trait no annotation expresses.

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?

Four tight clauses in one paragraph, front-loaded with the action and the sibling contrast before paging and safety details. Every sentence adds information an agent needs — nothing repeats the annotations or the schema types.

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 still covers the return shape (the exact text plus a full-text SHA-256) and the safety posture of the payload. The paging protocol is described only partially — the per-page limit and expected_rev behavior are clear, but how offset/paging terminates is not, which matters for a tool whose main use case is reading text larger than 4096 characters.

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 the description must carry the load, and it does for the two non-obvious parameters: limit (at most 4096 characters per page) and expected_rev (REQUIRED after the first page). The field enum, project_id, and node_id are reasonably self-evident, but offset is never explained in the description, leaving one paging parameter undocumented anywhere.

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 ('Read the exact saved text/prompt of ONE node of an account-owned Canvas project') with explicit scope ('ONE node'). It directly separates itself from the sibling canvas_read by noting summaries redact and truncate, so an agent knows which to pick without opening a schema.

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?

Names the alternative (canvas_read summaries) and gives the condition selecting this one — exact, unredacted, full text. It also states a per-page cap and the expected_rev requirement after the first page, which is real usage guidance. It stops short of stating when this tool should NOT be used (e.g., when only names/metadata are needed).

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