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

Goes far beyond the annotations: it discloses the two-phase preview/commit protocol, that a call without confirmation_token only previews, that the token is short-lived, that timezone is not an update input but is preserved and shown in the preview, and that untouched stored values are preserved and not re-asked. This is exactly the mutation-safety context an agent needs and is consistent with idempotentHint=true and destructiveHint=false.

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 sentences, no filler, with the most consequential rule (two-phase write, never infer values) front-loaded. The final sentence is long and packs preview-return shape, token reuse, and the confirmation gate into one clause chain, but every element is load-bearing.

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 16-parameter, zero-required mutation tool with no output schema, the description completely covers the safety workflow and what the preview returns, which is the hardest part. However, with 38% schema coverage it leaves a large share of parameters semantically unexplained, so an agent still cannot confidently choose which fields to send or what each does.

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 only 38% across 16 parameters, so the description must compensate and only partly does: it clarifies automation_id as required-in-practice, explicit values over defaults, the confirmation_token lifecycle, and the deliberate absence of timezone as an input. The many domain parameters (weekday, frequency, criteria, daily_time, lead_count, day_of_month, recipient_email, use_account_email) get no explanation beyond their names.

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 frames the tool as an 'explicit two-phase write' against a stored configuration identified by automation_id, with preview-then-commit semantics. It is clear what the tool does operationally, but it never states the concrete resource in plain terms (a lead automation's settings) nor distinguishes itself from siblings like update_trend_research_automation or create_lead_automation.

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?

Strong operational guidance: 'never infer or default configurable values', 'Supply automation_id and at least one explicit changed value', and 'repeat the identical call with the token after later user confirmation to write'. It covers the how-to-use flow thoroughly, but never names an alternative tool (e.g., create_lead_automation for new automations), so it stops short of full when/when-not routing.

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