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

Goes well beyond the annotations: it discloses the non-effect on the live site, the pre-write validation that refuses duplicate field names, orphaned optionScores and bad gateFields, that score ranges produce warnings rather than refusal, and that a retry duplicates the form. This is exactly the side-effect and failure-mode detail an agent needs for a destructiveHint write.

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?

Purpose is front-loaded and nearly every sentence carries information the agent cannot get elsewhere. The weakness is form: one long run-on paragraph with no bullets, which makes the scoring and calculator rules hard to scan.

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 large, deeply nested creation schema with no output schema, the description covers the critical semantics: validation refusals vs warnings, scoring modes, calculator breakdowns, and the retry hazard. An agent has enough to construct a valid call and anticipate failure.

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 100%, so baseline is 3, but the description adds real meaning on top: how optionScores are keyed by option id, how score mode sums points into scoreRange cards, what calculator.display/stats/parts do, and how optionParts must sum to each option's points. It is not a restatement of schema text, though it still leaves many nested objects (gatedAsset, autoresponder, conversational) to the schema.

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 ('Create a new form in a project') and immediately clarifies scope: the form is not on a page yet, so the live site does not change. That distinguishes it from update_form_schema, insert_section and create_page without the agent 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?

Gives clear conditional guidance for the risky case: 'A retry makes a second form: if the answer was lost, look for it with list_forms before trying again', naming the alternative tool and condition. It does not explicitly compare against update_form_schema, so an agent must infer that editing an existing form belongs elsewhere.

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