compute.submit_run

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

Annotations only supply readOnlyHint=false; the description adds real behavioral context beyond that: a confirmation gate (confirm=true), an input precondition (executable plan), and retry semantics via idempotency_key. It does not say whether the call is long-running or what a successful submission yields, which matters given the wait/progress siblings.

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?

Two short sentences, front-loaded with the action, then the preconditions and the retry property. Nothing is padded and no sentence is redundant.

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 no annotation coverage beyond readOnlyHint=false, the description covers gating and idempotency but not the result contract — whether submission returns a run handle to be polled via compute_get_run/compute_wait_run. That omission is the main completeness 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 description coverage is 0%, so the description carries the burden. It usefully explains confirm (must be true) and idempotency_key (makes retries safe), but plan_id — the sole required parameter — is only obliquely covered by 'a reviewed plan', with no indication of where the id comes from.

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 gives a specific verb+resource ('Submit a reviewed plan') and qualifies the input state ('reviewed', 'executable'), which separates it from the planning siblings like compute_plan_run. It stops short of naming which sibling produces the plan, so the differentiation is implicit rather than explicit.

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?

'Submit a reviewed plan' implies the plan-then-submit workflow and the confirm=true gate is stated, so an agent can infer it must plan first. There are no explicit when-not conditions and no sibling is named as the alternative, leaving the routing to inference.

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