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

Annotations already declare destructiveHint=true, and the description adds substantial context beyond them: it is a soft delete that frees quota, node-attached studies survive, and the call may return needs_confirmation requiring the agent to name the field and wait. That is exactly the behavioral detail an agent needs before invoking a destructive tool.

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?

Front-loads the core action and scope, then layers caveats and the confirmation flow. Every sentence carries information, though the dash-embedded clauses make it slightly dense to parse.

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 no output schema, the description still discloses the meaningful return state (needs_confirmation) and the confirmation protocol. Combined with full param coverage and safety annotations, nothing needed to call this destructive tool correctly is 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?

Schema coverage is 100%, so fieldId, workspace, and approvalId are already documented in the schema. The description reinforces the fieldId source and the needs_confirmation/approvalId loop but adds no new syntax or format semantics beyond what the schema provides.

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?

Names a specific verb and resource ('Removes a field and its whole canvas') and immediately scopes it as a soft delete that frees the workspace's field quota. This is clearly distinguishable from prism_fields_update/create in the sibling list.

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 an explicit when-to-use ('done with an exploration or one was created by mistake') plus a key side-effect caveat that studies are not deleted. It does not name an alternative sibling for the 'don't delete, deactivate' case, so it stops short of a full when-not/alternatives treatment.

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