build_wait

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered; the description adds genuinely new behavior — server-side blocking, a raise on timeout, and the subtle rule that strict_materials turns material-guard warnings into an error even when status is 'succeeded'. That last point is exactly the kind of non-obvious semantics an agent cannot infer.

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 doing distinct work: what it does, what failure looks like, and the strict-mode edge case. Blocking behavior is front-loaded, and there is 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?

An output schema exists, so return-value detail is unnecessary, and the description still notes that the run record is returned. For a long-blocking tool with error-on-timeout behavior, the essentials are covered; only an explicit pointer to build_status as the non-blocking alternative is missing.

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 67%, with timeout_sec and strict_materials already documented in the schema. The description adds meaning for strict_materials beyond the schema's phrasing by explaining the failure condition relative to the run's success status, and the timeout raise condition is reinforced. run_id is self-evident.

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 — block until the run finishes, then return its record — and the parenthetical '(server-side, no client sleep loop)' distinguishes it from the polling pattern an agent would otherwise use. It never names the sibling it replaces (build_status), so it falls short of 5.

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?

Clear context for when to call: you want to wait for completion rather than poll. Timeout behavior and the strict_materials escalation are spelled out. However, it does not explicitly route an agent to build_status for non-blocking checks or to build_cancel when waiting is undesirable.

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