Course Contacts

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorld, so the bar is lower; the trailing 'Read-only' largely repeats structured data. What the description does add is that the tool aggregates heterogeneous sources (syllabus-derived office hours, sign-up slots), which prepares the agent for a composite result. It says nothing about behavior when a course has no syllabus or no sign-up slots, or about result shape.

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?

One front-loaded sentence lists the three content groups in a natural order, with a short parenthetical tying output to a downstream tool. The trailing 'Read-only' is nearly redundant given readOnlyHint=true, a small wasted clause in an otherwise tight definition.

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 must convey what comes back, and it does enumerate the three result categories. For a one-parameter read tool that is close to sufficient, though it does not say whether the categories are returned as separate sections or how office-hour slots relate to appointment groups the agent could reserve via reserve_appointment_slot.

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?

There is a single parameter at 100% schema coverage, with the schema already telling the agent it is a numeric Canvas ID obtainable from list_courses. The description correctly adds nothing redundant, leaving the schema to carry parameter meaning; only the absent note about what happens with a malformed course_id keeps this from a full 5.

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 names a concrete resource set: teachers/TAs, office hours from the syllabus, and office-hour/advising sign-up slots within a course. That is specific enough to distinguish it from list_course_users (roster listing) and list_appointment_groups (generic appointment groups). It stops short of a crisp verb-plus-resource statement, reading more like an inventory of contents than a declared action.

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 phrase 'Who to contact in a course and when' implies the use case, and the parenthetical '(with the user IDs send_message needs)' usefully routes the agent toward send_message as a follow-up. There is no explicit when-not guidance and no mention of alternatives such as list_course_users, get_syllabus, or list_appointment_groups, so the agent must infer boundaries from siblings' names.

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