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

With no annotations, the description carries the full burden and does well: it discloses credit charging, automatic refund on failure, immediate return with run_no, and a 1-35 minute async duration. It stops short of stating auth/permission requirements or whether repeated calls are idempotent, so a small gap remains.

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?

Three short sentences, front-loaded with what the tool does, followed by cost/return behavior and the handoff chain. No filler and every clause carries actionable information.

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 an async job-start tool with an output schema and nested objects, the description covers cost, refund behavior, return timing, and the entire poll/result workflow. Missing only edge cases such as insufficient credits or duplicate-run handling.

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 for the top-level parameter is 0%, but the description compensates by pointing to app-list(slug=...) as the source of the exact input fields and by framing inputs as keyed by field id. It does not explain locale or brand_context_id behavior, which the nested schema covers.

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+resource ('Start one SupaMarketers App run') and immediately scopes it as an async job producer rather than a result fetcher. It names the sibling tools it hands off to (app-status, app-result, app-list), so an agent can place it in the workflow without opening any 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?

Explicitly describes the follow-up sequence: poll app-status, then fetch app-result, and get input fields from app-list(slug=...). The routing condition is stated, not implied, and the sibling alternatives are named with their respective roles.

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