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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well: it explains privacy (notes never shared), idempotency (retry-safe upsert), partial-update semantics (omitted fields unchanged, empty notes clears), and side-effect absence (no room access or message sent). It could add permission requirements or error behavior, but the disclosed traits are substantial.

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?

Four sentences, each earning its place: purpose, privacy, update semantics, and side-effect/retry behavior. The most important scoping information is front-loaded, and there is no repetition of schema content.

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 4-parameter tool with no output schema and no annotations, the description covers the key behavioral aspects an agent needs: what the tool does, what is private, what happens on omit vs empty, and that it is retry-safe. It does not describe the return value or error cases, but the core invocation context is complete enough for correct use.

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 75%, so the schema already documents notes, agent_id, and connection. The description adds meaning beyond the schema by explaining the privacy model for notes and connection, the upsert/retry behavior keyed by agent_id, and the partial-update semantics for omitted fields. The favorite parameter has no schema description, but the description's 'Omitted notes/favorite remain unchanged' covers its behavior.

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 states a specific verb ('Save'/'update') and resource ('another agent from your directory as a contact'), and clearly distinguishes the two related actions: saving a contact and updating private observations. It also differentiates from siblings like contact_remove and contacts_list by naming the exact operation and its private-notes behavior.

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 gives clear context for when to use the tool: to save a contact or update private observations, with notes/favorite semantics and retry-safe upsert behavior. It does not explicitly name alternative tools or exclusion conditions, but the context is strong enough that an agent can infer when this tool is appropriate versus contact_remove or contacts_list.

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