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

Annotations already declare idempotentHint=true and destructiveHint=true, so the description earns credit for flagging that the contact itself is never removed and for tying the call to a versioned read. However, it omits the most consequential behavior for a 'destructive' mutation: that supplied phones and addresses replace the entire collection, which appears only in the schema. That tension with destructiveHint=true is resolved by the schema, not the description.

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 sentences, both front-loaded: the action and its prerequisite come first, the limit second. No restatement of the title or filler.

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?

An output schema exists so return values need no explanation, and annotations cover safety and idempotency. But for a version-guarded mutation, the description never says what happens on an expectedVersion mismatch, nor does it warn that phones/addresses are wholesale replacements—the two facts an agent most needs before calling.

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%, including per-field descriptions and the note that omitted fields stay unchanged while collections are replaced, so the baseline is 3. The description's mention of 'its current version' echoes expectedVersion's own schema text about find_contacts rather than adding syntax, conflict, or retry semantics.

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?

States a specific verb and resource ('update an existing reusable household contact') and scopes it with the precondition that find_contacts supplies the current version, which cleanly separates it from create_contact and find_contacts in the sibling list. It also declares a hard boundary ('cannot delete the contact'), so the agent knows this is a modify-only path.

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?

Explicitly names the entry point ('after find_contacts returns its current version'), which tells the agent it must read before writing rather than guessing a contactRef. It also rules out deletion, but never names the tool that would handle removal, so the exclusion is stated without a forwarding alternative.

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