quickstart

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

With no annotations to lean on, the description still discloses key behavior: it runs as a background job requiring job_status polling, and it deliberately stops before paid rounds (cost boundary). It also notes the result names files to edit and the next command. It omits whether it writes to disk, whether re-running overwrites an existing folder, and permission/auth needs.

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 benefit ('Easiest start'), then the deliverables, then the key list, then the background-job caveat — a sensible order. The middle key enumeration is dense and comma-chained but each item carries call-relevant information; 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?

For a 4-parameter tool with a nested object and no output schema, the description covers what is produced, how completion is detected (poll job_status), and what the result contains. Missing pieces are the semantics of `url` and `no_run` and any statement of runtime or failure behavior, but the core calling information is present.

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 only 25% and the required `answers` parameter is an opaque nested object, but the description compensates well by enumerating its expected keys (brand, product with what/for-whom/price, buyers, platforms, tests, budget format like '300 USD', size enum, past_ads absolute path, docs). That is meaningfully more than the schema offers. The top-level `url` and `no_run` parameters remain unexplained.

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 concretely what the tool produces — a scenario folder with brief, personas, two template captions per platform, messages, launch calendar, pitch, plus simulated people — and marks the boundary 'stops before any paid rounds', which separates it from paid-test siblings like market_test or run_test. It never names or contrasts against the nearest onboarding siblings (setup, understand, start_live), so differentiation is implicit rather than explicit.

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?

'Easiest start' and 'stops before any paid rounds' imply this is the first-run entry point, and 'the exact next command' hints at a guided flow. However, no alternative tool is named and no condition for choosing this over setup, understand, or campaign_plan is given, so the agent must infer the routing.

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