update_contact

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

Annotations are absent, so the description must carry the full burden of behavioral disclosure. It reveals that the tool updates fields and imposes constraints (no property parameters, no line breaks), but does not describe side effects, whether updates are partial or full replacements, or what the return value looks like. For a mutation tool, this leaves essential behavior unspecified.

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 description is a single, front-loaded sentence that starts with 'PREFERRED' and immediately states the core action. The list of supported properties is comprehensive yet compact, and every sentence earns its place. It is slightly longer than ideal due to the list, but efficiently conveys the essentials.

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?

The tool has no output schema and no annotations regarding return behavior. The description does not state what happens after a successful update (e.g., returned contact, success message), nor does it mention the prerequisite of fetching an etag for conflict detection (though it is a required parameter). It also lacks guidance on typical usage flow in relation to the sibling tools. For an update operation, this leaves the agent uncertain about the outcome and sequence.

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?

The input schema already provides 100% coverage with detailed descriptions for every field (e.g., format examples for N, ADR, BDAY) and the constraint on property parameters. The description largely reiterates these details, adding only the 'without vCard formatting' phrasing, which is a minor clarification. Since the schema does the heavy lifting, the baseline of 3 is appropriate; the description adds little new meaning.

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 clearly states the tool's purpose: updating contact fields without vCard formatting, and explicitly lists the supported property names. It distinguishes itself from the sibling 'update_contact_raw' by emphasizing 'PREFERRED' and the non-raw approach, making its scope obvious to an agent.

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 description labels itself 'PREFERRED' and mentions broad support for RFC 6350 properties, giving a hint to prefer it over raw alternatives. However, it does not explicitly state when to use this tool versus 'update_contact_raw', nor does it mention scenarios where raw is required (e.g., property parameters). The note that property parameters are not accepted implies a limitation, but the alternative is not named directly.

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