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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the crucial detail that deleting a field also destroys its stored values, plus an explicit confirmation instruction. The {{cf.<key>}} template syntax on create is genuinely non-obvious context. It stops short of covering permissions or idempotency of set_value, so not a 5.

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?

A single dense sentence with parentheticals per action — no filler, and the entity scope is front-loaded. It is compact enough that the parenthetical caveats are the only slight readability cost.

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 10-parameter mutation tool with no output schema, the description covers the destructive path and the create template semantics, while required-parameter mapping per action is fully handled by the schema. It does not describe what set_value returns or whether updates to type affect existing values, which would be the remaining gap.

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 60%; the schema itself labels id, name, fieldKey, options, entityType and position as to which actions need them. The description adds meaning only for fieldKey (becomes {{cf.<key>}}) and value (one record's value). Parameters like type, entityId and value have no description text in either place, so it adds marginal value over the schema.

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 the resource (custom fields on contacts, companies, deals) and enumerates the four operations (create, update, delete, set_value), which cleanly separates it from the sibling read tool custom_fields_list. The lead is a noun phrase rather than a verb, so it is slightly less crisp than an ideal verb+resource statement, but the action list removes 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?

Gives per-action guidance: delete says 'confirm first', create explains the field_key placeholder, and set_value is scoped to 'one record's value'. It never states the inverse (use custom_fields_list to read fields), but the action enumeration makes the split with the list sibling inferable.

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