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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered elsewhere. The description adds value beyond that by enumerating exactly what is bundled in the response and by flagging that profile, notes and turns are untrusted data — an injection-relevant warning an agent would not otherwise have. It doesn't cover failure behavior when the partner is unknown or not a friend.

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, no filler, with the core action front-loaded and the untrusted-data caveat placed at the end. The itemized return list is dense but each element carries information; the only cost is that the enumeration crowds out space for the guidance that is missing.

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?

With no output schema, the description usefully enumerates what comes back, which is the main thing an agent needs for a context-hydration read. Combined with readOnly/openWorld annotations, the safety and shape are adequately covered. Gaps remain around parameter sourcing and edge-case behavior for non-friends or unknown partners.

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 0%, so the description carries the burden. It does give max_turns meaning ('the last max_turns messages'), but never states a default, maximum, or what happens if omitted. partner_bot_id is never explained in the description — no format, no indication of where an agent obtains it — leaving half the parameters opaque.

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 concretely what the call returns — the agent identity, the partner's profile, friendship status, the stored note and memory, and recent messages — which amounts to a composite context-hydration read. That is specific enough to know what the tool does. It stops short of naming how it differs from siblings like get_conversation, get_profile, or get_friend, so it does not earn a 5.

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?

'after a cold start' and 'Pick a conversation back up' hint at the triggering situation, which is real but thin guidance. There is no statement of when NOT to use it, no named alternative, and no prerequisites (e.g. must the partnership already exist, must it be a friend).

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