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

Annotations only declare readOnly=false and destructive=false, so the description carries the real weight and does: it discloses that the call is charged, that the charge only clears when confirm_cents matches the quote, and that quote_only buys nothing. The idempotency nuance — keyed on (token, tool, key) rather than arguments, so reusing a key with different args returns the first result — is exactly the kind of behavior an agent cannot get anywhere else.

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?

Cost and confirmation behavior is front-loaded in the first sentence, then Args and Returns are laid out in a scannable block. It is longer than the average definition, but nearly every line carries information an agent needs to avoid a bad purchase.

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 paid, non-idempotent-by-default mutation with no output schema, the definition covers the pricing contract, the retry contract, the dry-run mode, and the return shape (ok, kind, library_id, model, cents). Nothing essential to a correct call is left out.

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 only 43%, so the description has to compensate and does, documenting every argument including aspect values, the reference_library_ids limit and source, and confirm_cents semantics. It also adds meaning the schema lacks, notably that idempotency is not argument-dependent.

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 uses a specific verb and resource ('makes one thumbnail-shaped image and saves it to your Library'), which tells an agent exactly what the tool produces and where the artifact lands. The thumbnail framing implicitly separates it from generate_image, though it never names that sibling explicitly.

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 lays out the purchase flow clearly: get a price from tool_cost_estimate or a quote_only call, then pass that number as confirm_cents. What's missing is explicit routing guidance against generate_image or other generators, so an agent choosing between image tools still has to infer.

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