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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: it takes no arguments, reads only the credentials on this connection, and the returned values always describe the connected user regardless of any caller input — a useful guarantee the annotations cannot express. It does not specify any failure mode (e.g. no connected account) or caching behavior, keeping it short of a 5.

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?

Purpose is front-loaded, followed by usage triggers, exclusions, and return shape — a sensible order with no filler sentences. The final return-value sentence overlaps with the output schema and is the one piece that could be trimmed.

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 zero-config read tool, the description covers when to call, what it reads, what it guarantees, what it explicitly does not answer, and how the returned identifiers relate (id + team_id identify the account). Nothing needed for correct invocation is missing, and the output schema carries the return detail.

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% and the single parameter (user_intent) is client-supplied boilerplate already fully documented in the schema. The description correctly reinforces that the tool 'takes no arguments', so the agent understands user_intent has no bearing on the result. No additional parameter semantics are needed.

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 opens with a specific verb and resource: reporting which Canva account and Canva Team the connection is signed in as. No sibling tool in the list does identity/connection introspection, so an agent can route here unambiguously without opening a schema.

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 enumerates concrete triggering situations (multiple linked accounts, 'which account is connected', confirming whose account the next action affects, which team work is saved to) and then states explicit exclusions: other people's details, team memberships, team member lists, plan/billing status. That is both when-to-use and when-not-to-use, which is rare.

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