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

Path breaking: it discloses one-shot consumption, non-reversibility on failure, the enumerated refusal reasons with their exact codes, required scopes (actions.write, Agent Picks) and the human-permission requirement. This adds substantial context beyond the annotations and is consistent with destructiveHint=true and idempotentHint=false.

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?

Purpose is front-loaded in the first clause, and the transaction semantics follow before the operational details. The long enumeration of refusal codes is dense but each token is load-bearing for error handling; the run-on 'Requires actions.write and Agent Picks. The OAuth member...' tail is the only mildly cluttered part.

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?

There is no output schema, but the description supplies the return shape (status queued, test_id, runs), the follow-up tool, the authorization prerequisites and the full refusal taxonomy. An agent has everything needed to call this correctly and interpret both success and failure.

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 single `setup` parameter is fully documented in the schema (id or category slug, optional when only one setup, plus the agent_picks_setup_required / not_found error behaviour). The description adds only the phrase 'on its saved setup', so the schema does the heavy lifting and the baseline of 3 applies.

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?

Names a specific verb and resource ('Start the project's free Agent Picks starter test on its saved setup') and implicitly separates it from the read-only sibling by naming devtune_get_agent_picks_starter_test as the follow-up. The agent can tell from the description alone that this is the one-shot kickoff mutation, not the polling read.

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?

Gives a concrete usage condition — one per confirmed account-owner work domain — and states explicitly that queueing consumes it and that failure/cancellation does not restore it, which is the key decision input. It does not contrast against adjacent siblings such as devtune_quote_agent_picks_test or the scheduling tools, so the alternative-routing is only partially covered.

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