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

Goes well beyond the annotations (idempotent, non-destructive) by disclosing that fields replaces the entire list rather than merging, that removed fields' answers stay readable in exports and summaries, that a field with answers keeps its type, and that empty or null clears redirect_url/close_at/notify_email. It also surfaces concrete cost facts ($0.01 per call, billed only on success, $0.01 per on_response action), which no annotation conveys.

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?

Dense and front-loaded: the partial-update rule and the fields replacement hazard come first, then downstream answer-retention behavior, then clearing rules and cost. A few clauses are packed tightly (the clearing sentence carries three parameters), but nothing is redundant.

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 15-parameter mutation with no output schema, the description covers the risky behaviors (list replacement, type locking, answer retention, clearing semantics) and billing. What it doesn't state is what the call returns, which leaves the agent guessing about the response shape after a successful change.

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?

With 87% schema coverage the baseline is 3, but the description adds genuinely non-obvious semantics the schema does not: the difference between omitted and empty/null for redirect_url, close_at and notify_email, and that max_responses 0 means no limit. The fields replacement warning reinforces the schema's id note with the consequence (a renamed field becomes a new one).

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 specific verb and resource ('Change a form's fields or settings') and immediately disambiguates the operation as a partial update ('only what you pass changes'). That clause alone separates it from forms_create and forms_delete, which the sibling list otherwise leaves to inference.

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?

States clearly when a field must be passed back on update and points to forms_get as the source of field ids, which is the key precondition for safe use. It does not explicitly name alternatives such as forms_create or forms_delete, but the update-vs-replace framing makes the choice obvious.

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