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

Annotations declare the mutation/destructive profile, and the description goes well beyond them: it discloses asynchronous behavior (returns immediately as 'queued'), the polling contract, the failure/refusal semantics, and the special tiktok_warmup behavior (starts one session per phone, returns 'running' plus sessions/skipped_busy_slots). This is exactly the kind of behavior an agent cannot infer from the structured fields.

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-loaded with the core action and the async/polling contract, and every sentence carries information. It is dense and the tiktok_warmup paragraph is long, but it is not padding – each clause adds a behavioral fact the agent needs.

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?

With no output schema, the description compensates by naming the returned fields (id, status, sessions, skipped_busy_slots, outcome, result, phone_reports) and the exact state machine to wait on. For a 3-param, open-world automation trigger this is complete enough to call and follow up correctly.

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%, so the baseline is 3, but the description adds real meaning: it clarifies that payload is ignored for tiktok_warmup automations, and ties automation_id/slots to their source tools (list-automations-tool, list-phones-tool). The slots-omit-to-run-all behavior is also reinforced in prose.

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 ('Start one of the user's automations now') and anchors it to the familiar web-app 'Run now' action. An agent can immediately distinguish it from run-macro-tool and run-phone-agent-tool because it is scoped to a user automation by automation_id.

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?

Explicitly names the follow-up tool (get-automation-run-tool), the exact polling condition (until status is done, failed or stopped), and the fields to read afterwards. It also enumerates the refusal conditions (automation off, run in progress, daily limit, no phone online, agent unavailable), so the agent knows what a non-started response means.

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