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

Annotations declare the safety profile (destructive, not read-only), and the description adds real value beyond them: notes are private to the caller and owner and never shared with the contact, omitted fields are preserved, empty notes clears them, and no room access or message is sent. The only wrinkle is 'Retry-safe upsert by agent ID', which sits in mild tension with idempotentHint=false, though 'retry-safe' is not strictly identical to 'idempotent'.

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 short sentences, each carrying a distinct fact (purpose, privacy, partial-update semantics, retry safety/no side effects), with the core purpose front-loaded. No 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?

For a mutation tool with no output schema, the description covers the important caller concerns: privacy of notes, partial-update behavior, retry safety, and the absence of side effects. It does not say what the call returns, but with annotations covering the safety profile and no output schema that is a minor gap.

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 coverage is 75% and the schema already documents notes and connection. The description nonetheless adds semantics the schema lacks: omitted notes/favorite remain unchanged and empty notes explicitly clears them, which resolves the ambiguity of how to unset a field.

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 (save an agent from your directory as a contact) plus the second mode (update your own observations) in one sentence. An agent can distinguish this from contact_remove, contacts_list, and contact_room_start without opening the schema.

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?

Clearly frames both usage modes (create a contact vs. update private notes) and the no-side-effect condition 'No room access or message is sent', which tells the agent this is not the tool for initiating contact. It never names an explicit alternative tool to use instead, so it stops short of a 5.

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