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

Annotations only declare the flag set (not read-only, not destructive, not open-world, not idempotent); the description adds materially more. It discloses that no image is uploaded, that payment_ref is a 'paid escrow reference consumed by the gateway' (i.e. the call can cost money), and that request_id is a retry-safe key capped at 128 characters. There is mild tension between idempotentHint=false and a retry-safe idempotency key, but the two are reconcilable (idempotency only when the key is supplied) and it is not a contradiction.

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 summary sentence is front-loaded and the Args block is easy to scan. Every line carries information the schema does not, so the length is earned. The phrasing is a touch verbose in places ('Optional caller-supplied height for distortion check') but nothing is wasted.

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?

An output schema exists, so return values need not be described, and the description covers the remaining gaps: input provenance, the optional distortion-check parameter, payment semantics, and retry behavior. For a six-parameter computation tool with zero schema coverage, this is complete enough to invoke 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 0% and the objects array is a free-form object with additionalProperties, so the schema conveys almost nothing. The description compensates fully, documenting all six parameters plus the nested object contract (pixel_width and pixel_height required; label, pixel_area, pixel_perimeter, and confidence optional), the 128-character limit on request_id, and the billing role of payment_ref.

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: 'Scale object pixel dimensions using a standard CR80 credit card reference.' An agent immediately knows this is a geometric scaling/measurement operation anchored to a physical reference card. Sibling tools (credit_card_photo_instructions, describe, health) are unrelated enough that no explicit differentiation is needed, though none is offered.

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?

Usage is implied rather than stated: you call this when you have per-object pixel dimensions and a known credit-card pixel width. There is no explicit when-not guidance and no mention of the sibling credit_card_photo_instructions, which is plausibly the prerequisite step for obtaining a usable card reference. An agent can infer the context but is not routed.

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