Inbox

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

Beyond the readOnlyHint annotation, it makes the non-obvious guarantee that it 'never marks anything as read' — precisely the side effect an agent would worry about with an inbox tool. It also discloses the default unread filtering and the shape of returned entries, which 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?

Front-loaded with what the tool returns, then defaults, then pagination, then the safety note, then an example — each sentence carries distinct information with no padding.

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?

For a simple three-parameter read tool with no output schema, the description covers return contents, ordering, default filtering, pagination, and side-effect guarantees. Nothing an agent needs in order to call it correctly is missing.

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 description coverage is 100%, so all three parameters are already documented with defaults and bounds. The description restates the defaults (unread_only true, 20 per page) and frames limit/page as a way to 'step through long lists', adding intent but no new syntax or edge-case detail; 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?

The description names the specific resource ('Your Canvas inbox'), its ordering ('newest first'), and exactly what each entry contains (subject, participants, last-message time, preview). No sibling tool covers inbox conversations, so ambiguity is effectively zero.

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?

It states the default filter (unread only) and how to change it, plus how to paginate, and closes with a concrete user question ('Did any instructor message me in Canvas?') that triggers the tool. It stops short of naming when a different sibling (e.g. get_announcements) would be the better choice, but no sibling overlaps this resource.

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