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

Annotations declare destructiveHint=true and idempotentHint=true, and the description adds genuinely non-structured behavior: run requires user approval, preview produces a requestId/cost/readiness receipt that auto/run reuse, and execution returns task/status and possibly nextAction. It does not explain why the operation is flagged destructive or what the approval/rate-limit flow looks like, so it falls just short of full disclosure.

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 the core purpose and alternatives, then a compact workflow clause. It is information-dense with no filler, though the telegraphic 'receipt' phrasing and run-on clauses require careful reading.

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 5-parameter tool with one required param, no output schema and a destructive annotation, the description covers inputs, execution flow, approval gating, and even return fields (task/status, nextAction). What it omits is the specific consequence behind the destructiveHint and any failure/recovery modes.

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% (baseline 3), but the description adds operational meaning the schema lacks: requestId is a reusable preview receipt rather than a fresh input ('auto/run only, without new image inputs'), and action semantics tie into the preview/approval lifecycle. This is real value beyond the enum descriptions.

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?

Opens with a concrete verb plus resource and enumerated operations ('Apply x2/x4/anime/face to one image'), immediately distinguishing it from sibling tools. An agent can tell this is the dedicated upscaling tool without opening the 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?

Explicitly routes to alternatives: 'use derive_image for general edits and generate_image for new images.' It also explains the preview/auto/run lifecycle and that run requires approval, so the when-to-use decision is fully specified.

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