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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world mutation, so the safety profile is covered. The description adds one genuine behavioral rule not present in the annotations ("At least one optional field must be provided") and partial-update framing, but says nothing about permissions, whether the update is reversible, or how unspecified fields behave beyond what the schema already states.

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-loaded with the verb and affected fields, then a scannable "When to use" list, then the required-parameter constraint — a sensible ordering with no filler prose. The field enumeration in the opening sentence is partially duplicated by the bullets below, and the leading emoji is decorative, keeping it from a 5.

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 partial-update tool with annotations covering the safety profile and no output schema, the description supplies the essentials: what is mutable, how to obtain contact_id, and the at-least-one-field rule. It does not describe the response or failure modes (e.g., invalid or unknown contact_id), which is a minor gap given no output schema exists.

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 the baseline is 3. The description's field list and the contact_id provenance note largely restate what the schema already documents, including the clearing semantics ("empty string clears") and the omit-to-leave-unchanged rule for preferred_channel. No additional syntax, coupling, or interaction detail is contributed beyond 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?

The description gives a specific verb and resource ("Update a contact's profile") and enumerates the mutable fields (name, notes, role, capabilities, birthday, preferred channel), which separates it from sibling writers like contacts_add_channel or contacts_merge. It also pins down the entity being mutated via the contact_id provenance note. It stops short of an explicit "not this tool, use X instead" statement, so it lands just under top marks.

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?

A dedicated "When to use" block lists three concrete user intents (add notes, set role/capabilities, rename or set birthday), and a precondition is stated: contact_id is required and at least one optional field must be supplied. What's missing is the negative side — no guidance on when to prefer contacts_merge, contacts_profile, or contacts_capture_lead over this update.

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