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

Annotations are minimal generic hints (readOnly=false, openWorld=true, idempotent=false, destuctive=false). The desciption adds the load-bearing behavioral facts: the operation is Billed, requires confirmSpend=true only after a REAL human yes in a SEPARATE message, stores the result, and must not be retried on spending exhaustion. No contradiction with the annotations.

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 purose, then the billing gate, then the two mode branches, then failure handling and quality. Scannable typography (caps, arrows, em-dashes) keeps dense information parseable. Every clause carries operational weight and none of it repeats what the input schema already states.

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?

With no output schema, the desciption discloses the return (image_url + markdown preview). For a billed 6-parameter mutation it also covers storage location, the human-approval sequence, post-success actions (SHOW / place URL on page), and the spending-exhaustion path. Nothing needed to call it correctly is missing.

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 baseline is 3. The desciption adds meaning above the schema by explaining interdependencies: the forPage/sitePageId pair resolves the storage path, confirmSpend has an ordering requirement (separate-message human approval of prompt+quality+charge), and quality tiers are restated. Genuine added value, though not every param (e.g., style) is elaborated.

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 specific verb+resource+output: 'Generate a BRAND-NEW image via Gemini; stores it and returns image_url (+ markdown preview).' It names the engine, the side effect, and the return shape, and the 'BRAND-NEW' phrasing explicitly contrasts with the sibling regenerate_image so an agent can distinguish them without opening either 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?

Carves out the two usage modes explicitly: STANDALONE (omit sitePageId → account-root AI folder; SHOW the image after success) and PAGE/SITE (forPage=true AND sitePageId=<page id> → Sites/{site}/{page}/AI; propose prompt+quality+charge first). It also gives a when-not: 'On aiSpendExhausted: warn + Billing — do not retry.' The only implicit branch is regenerate_image for existing images, but 'BRAND-NEW' already signals that boundary.

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