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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true) it discloses genuinely useful behavior: conditions are replaced wholesale when supplied and {} clears them, the trigger is immutable, and live automations silently stop emailing members who no longer match. That side-effect disclosure is exactly the kind of context annotations cannot carry.

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?

Very short and mostly front-loaded, with the site constraint first and the conditions semantics and warning after. However, the telegraphic fragments ('A new name, the trigger's newsletter or label, or the conditions') cost readability and the sentence order is a bit scrambled.

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 6-parameter mutation with a nested object and no output schema, the description covers side effects and trigger immutability but says nothing about what a successful call returns or how idempotency manifests. It is adequate given rich annotations and high schema coverage, but not fully complete.

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 83%, so the schema already documents site, automation, conditions and the nested fields. The description adds the replace-all and empty-object semantics for conditions plus trigger immutability, but the replacement wording largely duplicates the schema's own conditions description, so marginal added meaning is modest.

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 never states a verb such as 'changes' or 'updates'; it opens with a site constraint ('On one site of the account, named in site') and then lists the mutable fields (name, trigger's newsletter or label, conditions). An agent can infer this edits an existing automation, and 'a new trigger is a new automation' implicitly separates it from create_automation, but the framing is oblique rather than a direct purpose statement.

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?

It gives one implicit routing rule — changing the trigger requires a new automation, i.e. use create_automation instead — and one explicit procedural caution ('say so to the person first' when members stop matching mid-flight). There is no explicit when-to-use/when-not framing against update_automation_step or the add_automation_* siblings.

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