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

Annotations already flag destructiveHint=true, so the bar is lower, yet the description adds real value: it explains what transit/none actually do (clear the per-form choice) and documents a refusal rule not present in annotations. It doesn't describe the response shape, but an output schema exists to cover that.

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 tight sentences, front-loaded with the core action, followed by the prerequisite and the two edge-case rules. No filler; every sentence carries an actionable 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?

For a mutation with an output schema and annotations covering the safety profile, the description supplies the key operational gotchas (provider must be connected, clearing rules, refusal on live file-collecting forms). Sufficient to invoke safely, though a note on reversibility would round it out.

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 only 50% schema coverage, the description compensates by giving semantics for the otherwise-undocumented destination enum values — specifically that 'transit and none both clear the per-form choice.' It restates the enum list from the schema but adds meaning beyond it.

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+resource ('Set where a form's uploads land') and immediately enumerates the destination values. It clearly reads as the write counterpart to fillo_get_storage and is distinct from sibling setters like fillo_set_drive_folder or fillo_set_branding.

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?

Provides a clear precondition ('The workspace must already have that provider connected') and refusal condition ('Clearing storage on a live form that collects files is refused'), which tells the agent when the call will succeed. It does not explicitly name an alternative tool, but the context is strong enough to invoke correctly.

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