update_cloud_flow

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is known. The description adds useful context beyond that: the ETag-based optimistic-concurrency gate, a preview/dry-run capability, and a post-write verification of the saved definition, plus the explicit statement that the flow is left disabled. It still omits what happens on ETag mismatch, permission requirements, and rollback behavior for a destructive mutation.

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 sentences, front-loaded with the core action, followed by the single most important exclusion. No filler wording and no restatement of the tool name.

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 destructive mutation with a nested object parameter, 20% schema coverage, and no output schema, the definition covers the important flows (preview, ETag-guarded replace, verification) but leaves key gaps: acceptable spec format, behavior on hash mismatch, and what the verification step actually confirms. Adequate but not sufficient for a fully safe invocation.

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 only 20% (only environment_profile is documented), so the description carries real weight here. It does gesture at three parameters – 'Preview' for dry_run, 'specific ETag' for expected_hash, and 'supported spec' for spec – but never uses the parameter names, so an agent must infer that 'ETag' maps to expected_hash, and the id parameter and the nested spec object's shape remain entirely unexplained.

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 names a specific verb and resource ('replace a stopped Online cloud flow with a supported spec') and adds the ETag precondition plus a post-write verification step. It is clearly distinct from read paths like get_cloud_flow and list_cloud_flows, though it never names its closest siblings (prepare_cloud_flow, create_cloud_flow, set_cloud_flow_state).

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?

The preconditions for use are stated concretely: the flow must be 'stopped', a 'supported spec' is required, and a 'specific ETag' must be supplied. It also excludes one adjacent action ('Does not enable the flow'), implicitly routing state changes to set_cloud_flow_state, but it does not explicitly contrast itself with prepare_cloud_flow or create_cloud_flow.

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