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

Adds rich context beyond the annotations: ~15 second latency, 3-credit cost with a 10-credit repaint tier, non-destructive versioning (every earlier version stays), and a required follow-up (poll get_run until terminal). The annotations already declare the mutation profile, so this is additive value; it stops short of only slightly on auth/limit details.

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 verb and resource, and each subsequent sentence carries distinct information (latency, cost tiers, exclusions, versioning). Slightly dense, but no sentence is 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?

An output schema exists, so return values needn't be explained, yet the description still tells the agent to poll get_run and surface the new image to the human. Combined with cost, latency, and the film exclusion, an agent can call this correctly without further context.

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%, so the baseline is 3, but the description adds real semantic guidance: 'Only what the instruction names changes' and the chaining example clarify how narrowly the instruction is interpreted, which the schema alone does not convey.

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 and resource ('edit a finished ad creative in place') and immediately clarifies scope: only what the instruction names changes, every other pixel is kept. It distinguishes itself from the closest sibling, render_asset, by ruling out films.

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?

Explicitly covers when to use it (chained tweaks on a finished still), when not to (films — use render_asset instead), and the escalation path when the instruction implies a full repaint (10 credits). The agent has no ambiguity about routing.

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