Start a test run

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

With annotations already declaring non-read-only, open-world, non-idempotent mutation, the description adds genuinely new behavioral context: the run consumes the workspace's usage allowance (session and month) and the optional wait is capped at 600 s. It stops short of stating what a run costs, whether concurrent runs are allowed, or that a run id is produced.

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 tight sentences with the core action front-loaded, then consumption cost, then the wait/hand-off pattern. No filler, though the parenthetical '(or AI exploration)' is the only hint that frontend_explore/frontend_flow kinds exist.

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 mutation tool with no output schema and openWorld=true, the description covers what triggers the run, its side effect on quota, and how to retrieve the result via siblings. It leaves the return shape (run id) and permission requirements implicit, but the routing to wait_for_run/get_run covers the main gap.

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 75%, so the schema largely carries the parameter burden. The description maps project type to the suite/frontend_health kinds and bounds wait_seconds, but says nothing about depth, max_pages, start_url, suite_ids, or environment beyond what the schema already documents. Baseline 3 is appropriate.

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 and resource ('Starts a run on a project') and explains what a run means per project type — API tests, website scan, or AI exploration. It does not, however, distinguish itself from the sibling start_scan, which an agent could easily confuse with the website-scan branch of this tool.

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 explicit routing for result retrieval: 'Optionally waits for the result (at most 600 s); otherwise use wait_for_run or get_run.' The kind/scope defaults per project type are also implied. No exclusion guidance against the sibling start_scan, and no prerequisites (auth/permissions) are stated.

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