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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false and say nothing about cost. The description discloses the two most critical behavioral traits: this is a BILLED operation that REQUIRES confirmSpend=true, and it stores a NEW file — which explains why destructiveHint=false despite the mutation. It also promises a concrete return (image_url + markdown preview) and rules out a side effect (no HTML patching). No contradiction with 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?

Four telegraphic sentences, each carrying a distinct fact: core behavior, return value, billing gate, and the two usage modes. The core edit/restyle behavior is front-loaded before caveats. The PAGE/SITE vs STANDALONE shorthand is dense but efficient — no sentence is redundant or filler.

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 billed, high-stakes mutation tool with no output schema, the description covers everything an agent needs to invoke it correctly: what it does, what it returns, the billing gate, the two invocation contexts, and what it deliberately does not do. The schema's confirmSpend human-approval requirement complements the workflow guidance. Missing error/rejection behavior is a minor omission against this level of coverage.

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 covers 100% of parameters with individual descriptions, so the baseline is 3. The description adds value by encoding workflow semantics: it binds forPage + sitePageId together for site edits, elevates confirmSpend to a hard gate ('REQUIRES confirmSpend=true'), and orders the flow as propose edit+quality+charge first. Minor gap: 'charge' is referenced but is not a named parameter, leaving the term slightly undefined.

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?

States a precise verb+resource pair ('Edit/restyle an existing image') and immediately differentiates from siblings: it stores a NEW file (vs generate_image creating from scratch), returns image_url + markdown preview, and explicitly says it does NOT patch site HTML. An agent can distinguish this from generate_image and import_image_from_url without opening schemas.

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?

Provides clear invocation context for the two modes — PAGE/SITE (forPage=true + sitePageId, propose edit+quality+charge first) versus STANDALONE (show the new image) — plus the required workflow ordering (propose before confirmSpend). However, it never names a sibling like generate_image as the alternative for creating new images, so when-not-to-use is implied rather than explicit.

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