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

Although annotations already declare destructiveHint=true, the description adds meaning that annotations cannot express: there is no undo and no trash, the public link stops working, funnel data is deleted with the responses, and NOT_FOUND after a timeout usually means the delete succeeded. The timeout and retry guidance ("a blind retry is not needed"; a read shows whether it went through) is exactly the kind of post-failure behavior an agent cannot infer from the schema. Nothing contradicts the annotation profile.

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?

The description is front-loaded: the scope is stated first, then the destructive consequences, then the confirmation protocol, then how to recover from errors. A few clauses are slightly redundant, such as restating "Destructive: it deletes or replaces data," which annotations already encode, and the closing sentence about the confirmation naming the form is a little loosely attached.

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?

With an output schema present and parameters fully documented, the description only needs to cover behavior and failure modes, which it does completely for a destructive single-object delete: scope, irreversibility, confirmation, and the timeout/NOT_FOUND ambiguity. An agent has everything required to invoke this safely without guessing.

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 100%, so both form_id and workspace_id are already documented with their sources (list_forms/get_form, list_my_workspaces) and the workspace_id conditional requirement. The description adds no parameter-level meaning beyond referring to get_form for the confirmation name, so the baseline of 3 fits.

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 ("Delete a form") and immediately widens the scope: "with every response and its funnel data," which tells an agent that this is a cascading delete, not a metadata removal. The distinguishing detail "Its public link stops answering" is unique to this sibling and cannot be inferred from the name alone.

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?

It gives clear usage context, saying that the agent should confirm with the user first and name exactly what will change, and it points to get_form for that name. It does not explicitly route away to alternatives such as deleting only responses or deleting a folder, so it lacks a stated exclusion, but the destructive-call protocol is spelled out clearly.

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