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

Annotations only flag it as a non-idempotent, non-destructive write. The description goes well beyond that: it edits the design's code via the editor's own linker, is recorded in version history with a named undo path (restore_version), and only reaches visitors after publish. It also discloses the side effect that Calendly linking enables the Calendly integration — a non-obvious state change.

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, action first, then the button-identification rule, then behavioral consequences. Every clause carries information an agent would otherwise have to infer; nothing is repeated from the schema.

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 an 8-parameter mutation with a nested options object and no output schema, the description covers the main call path, prerequisites, undo, and publish semantics thoroughly. The gap is the `calendly_options` styling/flags block, which is left entirely to the schema.

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 88%, so the baseline is 3. The description earns the bump by stating the conditional pairing the schema documents only field-by-field: `target: "form"` goes with `form_id`, `target: "calendly"` goes with `calendly_url`. The nested `calendly_options` sub-fields remain unexplained, so it isn't a 5.

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?

Opens with a concrete verb and resource — 'Make one or more buttons on the site open ... a popup form ... or a Calendly scheduling popup' — and names both target modes with their paired parameters. No sibling tool (add_redirects, validate_links, update_variation_file) could be mistaken for it.

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 spells out the prerequisite chain: button text must come from detect_page_ctas, `block` is required when the same text appears in multiple places, and `form_id` may be omitted when the site has exactly one popup form. What's missing is an explicit when-not or a named alternative for the case where the button should do something other than open a form/Calendly.

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