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

Annotations already declare destructive=true, idempotent=false and openWorld=true, so the bar is lower, yet the description adds real context beyond them: non-idempotent receivers will see duplicates, held responses are ineligible, and outward-facing ask-policy connections trigger a human approval link. These are the exact behavioral facts an agent needs before invoking a destructive, non-idempotent re-send.

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 short sentences, each carrying a distinct load: what it does, the duplicate consequence, and the hard exclusion plus approval caveat. The most important constraint (new delivery / duplicates) is front-loaded with zero filler.

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 return-value explanation is unnecessary, and the description covers the duplicate risk, the held-response exclusion, and the approval path. What is missing is scope detail on the input selection (max 200 response ids, what an invalid or unknown id does) for a tool whose blast radius is every destination of a form.

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 description coverage is only 50% – 'form' is documented in the schema, but 'responseIds' has no description at all, and the description text makes no reference to either parameter. With a documented gap rather than high coverage, the description should have compensated with format or limit details (e.g. the 1-200 id bound) and does not.

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?

Specific verb ('send responses again') and resource ('every current destination') with the key qualifier that this creates a NEW delivery rather than merely retrying. It implicitly separates itself from fillo_release_responses, but it never distinguishes itself from the close sibling fillo_retry_deliveries, leaving one plausible alternative ambiguous.

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 a clear when-not-to-use rule ('Held responses cannot be re-sent — release them instead') that routes the agent to fillo_release_responses, and warns about the approval-link step for ask-policy connections. It offers no guidance on when this is preferable to fillo_retry_deliveries, the nearest sibling.

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