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

Annotations cover idempotency and safety, but the description adds far more: required scopes (ai:generate, posts:write), credit costs per kind, the refund-once-failure policy, and that applied=false results are retained separately because user edits won. This is exactly the behavioral context structured fields can't carry.

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 purpose and prerequisites, and nearly every sentence carries operational information. The telegraphic, run-on style ('for 2+10*count credits') is dense and occasionally cryptic, but length is justified by the four-kind complexity.

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 complex, costly, mutating generation tool with no output schema, the description covers cost, prerequisites, idempotency, failure/refund behavior, follow-up polling, and result-state handling. An agent has everything needed to call it safely.

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?

With 0% schema description coverage, the description must carry the load and does: kind semantics, that maxCredits is a spend cap, that idempotencyKey must be stable and never charges twice, that references must belong to the profile, and that illustration needs projectId and slideId. This meaningfully exceeds what the raw schema exposes.

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 opening states a specific verb and resource ('Starts durable AI generation') and immediately enumerates the four kinds it produces. It clearly differentiates itself from siblings by routing to studio_quote for quoting, studio_job for polling, and studio_export for export.

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?

Gives explicit sequencing ('Quote first', 'Poll studio_job') and a spending policy ('Ask before spending unless already delegated'). It also names the alternative actions for export and publishing, so the agent knows what this tool does NOT cover.

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