run_start

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: the default bounds (30 min, 25 searches, 50 pages) and that 'earlier evidence persists' across runs. It does not explain what resuming a run actually does or what state is mutated.

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, front-loaded fragments with no wasted words; the core action comes first and defaults follow. It reads slightly telegraphic but 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 non-read-only tool with no output schema and 0% parameter coverage, the description is thin. It covers defaults and persistence but omits what a 'run' encompasses, what resuming entails, and how limits interact with the maximums enforced by the schema.

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 description coverage is 0% and the schema is a nested object. The description supplies defaults for the three limits fields, which partially compensates, but projectId (required) and idempotencyKey are completely undocumented in both schema and description.

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 pair (start/resume) and resource (bounded run), which is more informative than a bare name restatement. However, 'bounded run' is undefined jargon and the description never contrasts itself with the closely related sibling run_checkpoint, so an agent must infer the distinction.

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?

There is no explicit when-to-use, when-not-to-use, or alternative. The phrase 'start or resume' hints at two entry conditions but does not say how to tell whether a run already exists or when run_checkpoint (a sibling) would be preferred.

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