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

Annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description adds real value: it names the collateral damage (stored values are lost), discloses a precondition failure, and explains the two-phase confirmation protocol including that the first call is a no-op.

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 destructive effect and its blast radius, then the failure condition, then the protocol. No filler and nothing buried.

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 destructive tool with no output schema, the description covers effect, precondition, and safety protocol well. It stops short of saying what the preview actually returns (e.g., affected contacts) or whether the deletion is reversible, which would matter since no output schema exists to explain the preview payload.

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% and confirm/dry_run are already documented there, so the baseline is 3; the description earns an extra point by explaining the sequencing semantics of confirm (preview first, nothing deleted, then confirm: true) rather than merely restating the boolean.

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 custom contact field") plus the scope of destruction ("the values stored in it"), which distinguishes it from list_custom_fields and update_custom_field without any ambiguity.

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 prescribes the workflow: call without confirm for a preview, get an explicit yes from the user, then call with confirm: true. It also names the blocking condition ("Fails if the field is used in a webform"), which tells the agent when the tool will not succeed.

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