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

Goes well beyond annotations: discloses the confirmation-gated two-phase behavior, that reads sources but never posts, that pre-configured notifications may fire, idempotency binding, and retry semantics with the same key. Contradiction-free against idempotentHint/openWorldHint.

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?

Front-loads the core action, then sequences the flow logically. Dense but every clause carries operational meaning; slightly long but justified by the multi-step protocol.

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?

Covers the full confirmation workflow, side effects (notifications, no posting), retry behavior, and revision-binding edge case. Output schema exists so return values needn't be explained, and the description fills all remaining gaps.

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 0%, so the description must carry the burden and it does: it explains row_limit as the cap, confirmation as the returned token from the estimate step, idempotency_key must be reused on retry, and that approval binds the revision. Adds meaning the bare schema lacks.

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+resource ('Run an existing activated pipeline') and scopes it with the row cap. Explicitly distinguishes from siblings by naming get_run for inspection and stating it 'does not author code or change schedules.'

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 two-step protocol: first call returns estimate only, second call with confirmation starts the run, then inspect with get_run. Names the sibling to use afterward and the prerequisites (user approval, fresh estimate if revision changes).

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