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

Annotations indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false, which already tell the agent this is a mutating, non-destructive, non-idempotent operation. The description adds valuable context: it explains that imports always land as drafts because the status parameter is ignored for safety, and that passing back posts from preview prevents re-reading or changing them. It also clarifies the two different input handling paths. No contradiction with annotations; the description reinforces and extends the safety profile.

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?

The description is two sentences and packs essential information with zero waste. It front-loads the core purpose and then immediately gives the critical workflow instruction. Every sentence earns its place; there is no redundant content or filler.

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?

Given the tool's complexity (10 parameters, nested posts object, and two distinct modes), the description is remarkably complete. It covers the core behavior, the correct sequence of operations, and the safety guarantee about drafts. It does not explain every parameter, but the schema already does that. There is no output schema, so the description does not need to explain return values. The workflow guidance is sufficient for an agent to call this tool 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 the baseline is 3. The description adds meaningful context beyond the schema by explaining the semantics of key parameters: the 'mode' parameter's role in detecting planning documents versus artwork, and the 'posts' parameter as confirmed/edited output from preview_canva_plan. It also clarifies that 'status' is ignored and always results in drafts, which is not fully apparent from the schema alone. This additional explanation helps the agent understand the interactions between parameters.

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 clearly states the tool imports Canva designs into a content plan and explains the two distinct outcomes: planning documents become a full schedule with copy, single creatives become artwork with AI-drafted copy. It also differentiates from the sibling preview_canva_plan by prescribing a workflow that begins with the preview. The specific verb 'import' plus the resource 'Canva designs' and the target 'content plan' make the purpose unambiguous.

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 description gives explicit workflow guidance: 'Call preview_canva_plan first, show the user the copy and dates, then pass those posts back here so nothing is re-read or changed.' This tells the agent the correct sequence and that re-reading should be avoided. It also implicitly distinguishes between plan_document and artwork modes by describing both cases, though it does not explicitly state when to force one mode over the other. Overall, the usage context is clear, but it could be more explicit about exclusions or when not to use the tool.

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