start_trace

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

With no annotations provided, the description discloses key behaviors: takes 60-90s, costs credits, may return cached report slug for free, and requires polling via get_trace. This covers time, cost, caching, and async nature, though it omits failure modes or authentication requirements.

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 sentences, each informative: what it does, cost/time, caching behavior, and follow-up action. No 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?

For a 2-parameter async tool with no output schema, this description covers the essential operational details: duration, cost, caching, return value, and next step. It could mention how to consume the slug, but given the sibling tools, it's adequately complete.

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 input schema already describes both parameters (url and refresh) with 100% coverage. The description adds context about the cached report behavior that relates to the refresh parameter, but does not add significant new parameter-level meaning.

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 the tool's function: tracing a product's growth across 12 sources. It distinguishes from sibling get_trace by explicitly directing users to poll progress with that tool, and other siblings are clearly different (search, read, unlock).

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?

Provides clear context that this initiates a trace and that get_trace is for polling progress. However, it does not explicitly mention when to use this over other sibling tools like search_reports or read_report, though these are evidently different operations.

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