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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds concrete substance: the steps execute right away and real emails get sent, and the trigger step must be system.manual. That tells the agent the blast radius is immediate and non-simulated, which annotations alone do not convey. It stops short of saying what happens to failures or whether repeated calls create duplicate runs.

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 sentences, front-loaded with the action, then the side effect, then the precondition. Nothing is redundant and the most important warning (real emails are sent) is placed early.

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?

Complete enough to invoke correctly: verb, side effects, precondition, and payload routing are all present, and no output schema is needed for correct calling. The remaining gap is what the call yields (run ID / how to inspect or cancel the resulting run), which would help an agent close the loop but is not required to trigger safely.

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 100% and documents id as aut_xxx plus a generic payload object, so the baseline is 3. The description adds meaning the schema lacks by specifying that contact automations require payload.contact_id, which is more precise than the schema's email example. The payload shape for non-contact automations remains unelaborated.

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: start exactly one run of an already-running automation, immediately. The phrase 'one run of a running automation' implicitly separates it from start-automation (which presumably enables the automation itself) and from cancel/pause/stop siblings, though it never names those siblings explicitly.

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?

Provides a hard precondition (the automation must have a system.manual trigger step) and a routing rule for contact automations (pass payload.contact_id), which are genuinely useful. However, it never names an alternative tool or says when to choose start-automation, pause-automation, or get-automation-run instead, so sibling routing is left to inference.

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