List Conversations

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so "Read-only" repeats structured data and earns nothing. What does add value is the disclosed result ordering ("newest first") and the enumerated return fields. Nothing is said about pagination or how the limit interacts with the sort.

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 tight sentences: contents and ordering first, then the read-only/safety note, then the routing pointer. Every clause carries information and nothing is repeated.

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 compensates by naming the fields returned (subject, participants, last message preview, unread state) and the sort order. For a zero-required-parameter read tool that is sufficient to call it correctly.

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 limit, scope (with enum values) and filter are already documented in the schema. The description adds no extra semantics about them beyond implying the newest-first sort, so 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?

Specific verb plus resource ("List your Canvas Inbox conversations") with the scope of the returned data spelled out (subject, participants, last message preview, unread state) and an explicit ordering ("newest first"). Clearly separable from get_conversation and the mutation siblings like archive_conversation.

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?

Explicitly routes to get_conversation for the full thread, which is the main alternative an agent would consider. It gives no guidance on the mailbox variants (scope) or on when to prefer get_unread_conversation_count, so usage is clear but not fully fenced.

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