Send Peer Review Inbox Messages

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

Annotations only declare idempotentHint=false and destructiveHint=false, so the real behavioral burden falls on the description — and it delivers: real messages go to students, the first call is side-effect-free preview, and the send is gated on educator approval. This is exactly the context annotations cannot convey.

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, front-loaded paragraphs: purpose, the important negative distinction, then the two-step workflow. No filler and the most consequential constraint (approval gate) is not buried.

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 everything needed to call it correctly: what it sends, what it is not, the two-call protocol, and what the preview contains. An output schema exists, so return-value explanation is correctly omitted.

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 baseline is 3, but the description adds real meaning for confirmation_token (omit to preview, supply with identical arguments to send) that the schema merely restates as 'Token from the preview call; omit to preview'. Other parameters (recipient_ids, custom_message, subject_prefix) get no additional treatment beyond the schema.

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 ('Send'), a specific channel ('Canvas Inbox messages'), and a specific subject matter ('incomplete peer reviews'). It also explicitly disambiguates from Canvas's native peer-review reminder action, which an agent might otherwise assume.

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 a clear, explicit usage protocol: call without a token to preview, show the preview to the educator, then recall with the token and identical arguments to send. It does not, however, distinguish this from sibling tools that also send messages (send_conversation, send_bulk_messages_from_list, send_peer_review_followup_campaign), leaving that routing to inference.

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