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

Annotations carry only readOnlyHint=false, so the description does the heavy lifting and does it well: it discloses the 1-credit cost, the return artifact (a file_id), and how that value is consumed downstream. These are concrete operational traits an agent needs before calling a metered generation tool.

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 action and cost, and every clause carries signal (cost, gating, prompt guidance, exclusion, return value). It is a little dense and run-on in the middle, but not padded.

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, but the description compensates by explaining the return value and its downstream use, plus cost, size purpose, and prompt-construction guidance. For a 2-parameter generation tool this is complete enough to call 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 coverage is 100% and the size enum is exhaustively documented, so the baseline is 3. The description nonetheless adds meaning by clarifying that size is 'the canvas it will go on' and by prescribing what the prompt should contain (scene, light, empty space for the headline), which goes beyond the schema's terse 'The scene, in a sentence or two.'

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?

Specific verb (Generate) plus resource (a photo/background to sit behind a social image), with the scope made unambiguous. It also distinguishes itself from the sibling generate_og_image by stating this output feeds that tool's background_file_id. An agent can route between the two 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?

Gives an explicit gating condition: 'Only when the user asks for a photo, picture or background.' It also states the composition intent (leave empty space for the headline) and a hard exclusion ('never ask for text, words or logos'). It stops short of naming generate_og_image as the alternative for the full composite, leaving that to inference.

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