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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it warns that fields replaces the entire list, reassures that submit URL, stored enquiries, and email routing survive a rename, and discloses that the return value includes regenerated HTML that changes with the fields. That is exactly the kind of consequence detail an agent needs before a destructive mutation with no output schema.

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 verb and resource, and every clause carries information — the replacement semantics, the preserved data, and the HTML return. It is a single dense sentence-cluster with nested parentheses, so it reads as slightly packed rather than crisply segmented, but nothing is wasted.

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 5-parameter destructive mutation with no output schema, the description covers partial-update semantics, data preservation, status toggling, and the return shape. It leaves out permission requirements and what happens on invalid field definitions (e.g., a select without options), which is the remaining gap.

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 80%, so the schema already documents status, successMessage (including the empty-string default behavior), and the fields list. The description adds genuine semantics on top: the wholesale replacement of fields and the fact that omitted parameters are left untouched, which is the key contract for an optional-parameter update tool.

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 and resource ("Changes an existing form in place") and enumerates the four mutable surfaces: name, fields, success message, and submission status. This makes it trivially distinguishable from create_form, get_form, and update_site without opening any schema.

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?

The phrase "existing form" and the in-place partial-update rule ("Anything not sent stays as it is") tell the agent this is the modification path rather than creation, and the parenthetical on "paused"/"active" gives actionable context. It stops short of naming sibling alternatives or stating prerequisites, so it is clear-context rather than explicit when/when-not guidance.

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