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

Annotations already declare idempotentHint=true and destructiveHint=true; the description adds the important PATCH behavior that unspecified fields are left untouched, which materially informs an agent about mutation scope. It stops short of saying whether overwritten values are recoverable or what the response body contains, but the key behavioral fact is stated.

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?

Two short, front-loaded clauses with zero filler — the operation class and the partial-update rule come first, with the endpoint as trailing technical detail. Every element earns its place.

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 7-parameter mutation with low schema coverage and no output schema, the description covers the essential mutation semantics but leaves per-field meaning and return behavior unaddressed. Adequate to invoke correctly, but not rich enough to be fully self-sufficient.

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 only 29%, so the description must compensate; it does so partially by explaining that all field parameters are optional and only supplied ones apply. It gives no guidance on individual fields (first_name vs last_name, phone vs mobile) or on hash_key versus id, but the core optionality semantics are covered.

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?

Starts with a clear 'WRITE' marker plus a specific verb and resource ('change fields of a contact'), and the parenthetical clarifies partial-update semantics. It is distinguishable from create_contact/list_contacts by the 'change fields' phrasing, though it never explicitly names those siblings as alternatives.

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?

The parenthetical 'only the fields you pass are sent' implies when this tool is appropriate (patching an existing contact) versus a create call, and usage is reasonably inferable from the 'WRITE' prefix. However, there is no explicit 'use this instead of X when Y' routing or stated precondition (e.g., contact must already exist).

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