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

The description discloses key behaviors beyond annotations: it never publishes media, saves real Studio creatives, requires a seat and idempotencyKey, and returns internal application state for orchestration. It also explains response handling (not displaying raw JSON, using assistantSummary, suggesting next steps). These details significantly enrich the safety and usage profile beyond annotations like idempotentHint=true and destructiveHint=false. 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?

The description is dense but well-structured, front-loading the purpose in the first sentence, then phase details, then requirements and response guidelines. Each sentence adds useful information for an AI agent. It is somewhat long, but justified by the tool's complexity (16 params, two phases, interaction safety). The response-handling instructions are somewhat lengthy but relevant for correct agent behavior.

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?

Given the tool's complexity (16 parameters, nested objects, multiple phases) and the presence of an output schema, the description covers the essential operational aspects: phase purpose, required preconditions, mutation safety (never publishes), and how to present results. It doesn't explain every parameter, but the schema provides names and types. The only minor gap is that it doesn't explicitly state what the output schema contains beyond 'internal application state', though it mentions previews and QA evidence.

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?

The description adds semantics for critical parameters: 'phase' is clarified as having 'territories' and 'build' modes, 'idempotencyKey' is required for build, 'seatId/seatName' are required for mutations with multiple seats, and 'selectedTerritory' is the object from the territories phase used in build. This compensates for the 0% schema coverage for these non-obvious parameters. Other required fields (brand, campaignName, product, audience, objective) are self-explanatory from their names, so the lack of description is less critical.

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?

The description clearly states it is a 'one-prompt campaign builder' with two distinct phases ('territories' and 'build'), and specifies what each phase does: creating three AI creative territories, then executing the selected territory through run_creative_chain, saving creatives, building ads, and returning previews/QA evidence. It also distinguishes itself from siblings by noting it 'never publishes media,' which separates it from launch/launch_creative_campaign tools.

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 description provides clear usage context: it explains the two-phase flow, notes that a LeanrIQ seat is required and idempotencyKey is required for build, and gives response-handling guidelines (use assistantSummary first, don't show raw JSON). It also specifies when seatId/seatName must be supplied on the exact call. However, it does not explicitly name alternative tools or say 'use this when X instead of Y,' though 'never publishes media' implies when you don't want to launch.

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