Update Contact

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true, openWorldHint=true), so the description only needs to add context. It does add the field-scope constraint, but omits the behavior that matters most for a destructive update: whether omitted fields are left untouched or cleared, and how the appendMultiSelectValues replace-vs-append flag interacts with the rest of the payload.

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 scoping constraint and the sibling redirect are front-loaded and waste no words. The leading line "Update Contact." merely restates the title and is dead weight, but the remainder is tight.

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, open-world mutation with a large free-form body object and no output schema, the description covers scope but not outcome: it does not say what the response contains or whether partial payloads are safe. The custom-property and multi-select details live in the schema, so the remaining gap is behavioral rather than structural.

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 the body schema itself documents the custom-property convention (x_ prefixed keys via list_properties) and the appendMultiSelectValues semantics, so the description carries no additional burden. The description adds no parameter meaning beyond the schema; 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?

"Updates an existing contact by ID" gives a specific verb and resource, and the follow-up sentence narrows the resource boundary (contact fields only, not contact persons), which separates it from update_contact_person. It stops short of distinguishing it from the other write paths in the sibling list, notably create_contact and upsert_contact_by_email, so an agent must infer that this one is ID-addressed and edit-only.

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 explicitly names a when-not case (contact persons, including changing the main contact person) and points to the Contact Persons tools as the alternative, which is real routing guidance. It gives no guidance on choosing between this and upsert_contact_by_email or create_contact, and says nothing about prerequisites such as needing an existing contactId.

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