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

Annotations already declare mutating (readOnlyHint=false), open-world and non-idempotent behavior, so the description must add something beyond that, and it does: the email is appended after the preceding step and carries a wait, and an existing post 'the automation sends and never copies'. However, key mutation facts are unaddressed — whether supplying both post_id and title/markdown is rejected, what gets returned, and what error a bad site/automation produces.

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?

Four short sentences with little filler, but the elliptical, article-dropping style ('It goes its wait after the step before', 'never on the site') forces re-reading. The core operation is not front-loaded in a plain statement; it is buried in a fragmentary first sentence.

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 7-parameter mutation tool with no output schema, the description covers the essential semantics: placement at the end of the automation, the two post sources, and wait positioning. It leaves out what the call returns, precedence rules when both post sources are given, and any permission or failure context.

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 description coverage is 100%, so the schema already documents every parameter, including wait defaults and the 'Instead: a post that exists' hint for post_id. The description reinforces the mutual-exclusion intent between post_id and title/markdown and clarifies that the wait applies after the previous step, but adds no syntax or validation detail beyond that.

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 names a specific verb and resource — adding an email at the end of an automation on a given site — and distinguishes two modes: a new email built from title+Markdown, or an existing post referenced by post_id. The telegraphic phrasing ('An email at the end of the automation') is awkward but the operation and its variants are identifiable; it only stops short of positioning this against sibling step tools like add_automation_action.

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 conditional guidance for the two invocation modes: use title and Markdown for a new email, use post_id for a post that already exists (draft or sent). It also names the follow-up alternative explicitly ('edit_post changes a new email later'). It does not say when to prefer this over add_automation_action or update_automation_step, so exclusion guidance is incomplete.

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