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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes well beyond them: it names the exact destruction scope (form, every response, files), declares irreversibility, discloses the two-step single-use-approval flow, and warns that live embeds and the hosted URL break after approval. This is exactly the behavioral context the annotations cannot supply.

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?

Two tight sentences, front-loaded with the destructive scope before the approval mechanics and side effects. No sentence is filler; each adds a distinct fact.

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?

An output schema exists, so the approval-link return value need not be detailed further. Combined with the destruction scope, irreversibility, authorization requirement, and embed/URL side effects, the definition leaves nothing an agent needs missing.

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?

Only one parameter and schema description coverage is 100% ('Form id, slug, or push handle'), so the schema carries the semantics. The description adds no format or identifier guidance beyond it, making the baseline 3 appropriate.

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 (delete) and resource (form) and immediately expands scope to 'every response, and their files', distinguishing it from siblings like fillo_delete_response and fillo_delete_respondent. An agent can tell exactly what is removed without opening the 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 operating context: the tool never runs directly and instead returns an approval link a workspace owner or admin must confirm, which tells the agent what to expect and who is authorized. It does not, however, name alternatives (e.g., unpublish_form to merely take a form offline), so the when-not-to-use case is left implicit.

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