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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description still adds real context: permanence/irreversibility and the non-obvious fact that existing submissions retain their answers. It does not cover permission requirements or error behavior, so it falls just short of fully rich behavioral disclosure.

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 with zero filler: the destructive scope leads, then the data-retention nuance, then the safer alternative. Every sentence carries distinct information.

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, return values need not be explained, and the description covers the remaining agent-facing needs: irreversibility, user confirmation, and the safer alternative path. Nothing material is missing for correct invocation.

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 all three parameters (pageId, fieldId, pageType) are already documented in the schema, including how to obtain fieldId and which pageType to use. The description adds no additional parameter-level meaning, so the baseline 3 applies.

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 (one custom field) plus the exact scope of page types it applies to (checkout page, form, event). The contrast with update_field makes it easy to distinguish from the adjacent mutation sibling without opening either 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?

Explicitly says when to use this (permanent removal) versus when to use an alternative (update_field with hidden: true when the field should just stop showing). It also instructs the agent to confirm with the user first, which is actionable routing guidance.

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