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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description adds genuinely new behavior: it costs no Ad Run credit and consumes no AI turn, plus it returns { ideaId, imageUrl, applied }. It stops short of saying whether an existing hero image is replaced or what happens if the job has no such result id. Note a mild tension: 'set' reads as idempotent while idempotentHint=false, but this is a definitional nuance rather than a direct contradiction.

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 action sentence, then a compact args block that adds semantics rather than merely restating types, then return shape and cost note. Every line contributes; nothing is padding.

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 description supplies the return shape itself, and it covers preconditions and cost for a mutation tool. It is nearly complete except for the undocumented response_format parameter and the unstated effect on any pre-existing hero image.

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 0%, so the description carries the burden and largely does: it explains jobId's required state ('succeeded') and selectedResultId's origin ('the variant id from that job's results'). The fourth parameter, response_format with its markdown/json enum, is never mentioned in the description or the schema, leaving one gap.

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 and resource: 'Set one generated variant as the idea's hero image.' That verb ('set ... as hero image') is cleanly distinguishable from the sibling that generates variants and the sibling that fetches job status, so an agent can pick it 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?

The argument notes encode the workflow precondition: jobId must be 'a succeeded image job' and selectedResultId must be 'the variant id from that job's results', which tells the agent it must call generate/get_image_job first. There is no explicit when-not guidance or naming of the alternative tools, but the sequencing is unambiguous.

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