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

With no annotations at all, the description carries the full behavioral burden and it discloses exactly one real trait: 'Runs synchronously', which tells the caller no job polling (get_job) is needed. It says nothing about cost/credit consumption, rate limits, or what happens on refusal, which are the material behaviors for a paid media-generation call.

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?

Two sentences, zero filler, and the most decision-relevant facts — what it produces, the exact kinds, and synchronous execution — are front-loaded and compressed into fragments that still parse cleanly.

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?

There is no output schema and no annotations, so the description would need to say what comes back (asset URL? id? job reference?) and whether the call consumes credits, given that pricing/balance/payment siblings exist. It covers shape and execution mode but leaves the return value and cost profile entirely unspecified for a tool with three required parameters.

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 50% (prompt and owns_rights documented, kind and style not), and the description compensates by mapping the three enum values to concrete intents and adding banner dimensions (1536x512 / 1500x500) that appear nowhere in the schema. The one remaining gap is 'style', a 400-character free-form string with no explanation of expected content or examples.

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 specific verb (generate) and resource (one still image) and enumerates the three supported kinds, so an agent knows exactly what it produces. It partially distinguishes itself from kit siblings via 'one still', but never names generate_banner or generate_logo_kit, so the overlap with generate_banner (which accepts the same 'banner' kind) is left ambiguous.

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?

No explicit when-to-use/when-not guidance or prerequisites beyond the schema's owns_rights flag. The phrase 'Generate one still' implicitly signals single-asset usage versus the kit siblings, but the agent must infer which tool to pick when it wants a banner, since both this tool and generate_banner appear to cover it.

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