Create a sandbox account

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

Beyond annotations, the description reveals critical runtime behaviors: refusal is free, empty contact is rejected before any request, non-idempotency ('Calling twice creates two accounts'), and that the server continues using AVITO_ADS_ACCOUNT_ID rather than adopting the new one. These details align with the annotations (openWorld, non-idempotent) and add significant contextual depth.

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 compact and front-loaded with the most critical constraint ('SANDBOX ONLY'). Each sentence provides distinct, non-redundant information—environment, contact validation, idempotency, and post-creation configuration—without wasted words.

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 (9 params, nested object, no output schema), the description covers environment prerequisites, error/failure modes (refusal, empty contact), side effects (non-idempotent), and what to do after creation (update config). It fully equips the agent to use the tool correctly and anticipate outcomes.

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. The description adds emphasis on the contact object with an example and clarifies that an empty object is rejected, but this mostly repeats schema details. No additional parameter semantics are provided for the other eight parameters beyond what the schema already documents.

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 states a specific action—'creates a test advertiser account'—and names the return value ('returns its accountID'). It distinguishes itself from siblings by explicitly marking it as 'SANDBOX ONLY' and clarifying it cannot edit/delete accounts, unlike other account 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 clearly specifies the sandbox-only condition and explains that the call is refused outside that environment, which guides when to use it. It also states what it cannot do (edit/delete) and that the new ID must be manually placed into the config, but it does not explicitly name alternative tools for those tasks.

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