send_message

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the key group_conversation distinction (one shared conversation vs. separate 1:1s), which is a significant behavioral trait. However, it does not mention what happens if subject is null, what course_identifier does, or any side effects like sending emails vs. inbox-only. The most important nuance is covered, but other behavioral aspects are missing.

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?

The description is concise, with three sentences split across two clear points: the action and the parameter usage. It front-loads the primary purpose and then adds essential usage details. No wasted words, no redundancy.

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?

The description covers the main usage (send, group/individual, recipient sourcing) but omits important input details like purpose of course_identifier and subject behavior. Output schema exists, so return values are covered. For an agent to correctly marshal parameters, missing semantics for 2 parameters could cause incorrect calls. While the tool is simple, the description is not fully complete.

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?

The schema has 0% description coverage for its 5 parameters, so the description must compensate. It does explain reciprocity_user_ids (comma-separated, from list_users) and group_conversation (boolean effect). However, subject, course_identifier, and body are not described. Body is self-explanatory, but subject and course_identifier remain ambiguous. The description covers the two most critical parameters but leaves others unexplained.

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 clearly states the action: 'Send a Canvas Inbox message to one or more users.' It specifies the resource (inbox message) and the target (users), and distinguishes itself from sibling tools like create_announcement or post_discussion_entry by focusing on direct messaging. The group vs. individual behavior further clarifies its specific function.

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?

The description provides practical guidance: it tells the agent to get recipient IDs from list_users, and explains when to set group_conversation=True vs. False. It implies use for inbox messaging rather than announcements/discussions, but does not explicitly state exclusions. The guidance is clear enough for correct tool selection in most contexts.

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