canvas_conversations

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restating. The description adds useful behavior beyond that -- newest-first ordering and the inbox-as-default for scope -- but says nothing about result volume, whether paging is required, or what a returned conversation contains.

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?

Two compact sentences, front-loaded with the verb and resource, then immediately the disambiguation. Every clause does work -- the Gmail comparison prevents a real domain mix-up in a school-context toolset.

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 three-parameter, no-required-argument list tool with no output schema, the description covers what is listed, ordering, and the drill-down path. The main remaining gap is the shape of a returned conversation (HTML body, participants), which the agent must discover by calling it.

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 all three parameters (raw, page, scope) are already documented in structured form. The description only restates the scope enum values and the inbox default; it adds no meaning for raw or page beyond the schema, so the 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?

It states a specific verb and resource ('List Canvas Inbox conversations') and pins the scope ('newest first', scope picks unread/starred/archived/sent). It also explicitly separates itself from the sibling canvas_conversation ('Read one in full with...') and from Gmail, so an agent can pick it out of a large sibling set.

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 tool names its natural follow-up alternative ('Read one in full with canvas_conversation') and gives the condition that selects it, plus the default when scope is omitted. It doesn't mention other plausible siblings such as canvas_unread_count or canvas_activity_stream, and offers no explicit when-not-to-use guidance.

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