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

Annotations only declare readOnlyHint=true, and the description adds real behavioral context beyond that: login required, PRIVATE facts used only for matching versus PUBLIC shown on the profile homepage, a hard cap of 20 entries with oldest-first eviction, and that expired need preferences can be cleaned up. These are exactly the side-effect-ish traits an agent cannot infer from a bare read annotation.

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 auth requirement is front-loaded, which is good, but the body is a compressed run of slash-separated jargon (WANT/AVOID, PROFILE/NEED/TEMP) that forces the reader to decode rather than read. Every clause carries information, yet the shorthand makes it harder to scan than a slightly longer plain-language version would be.

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?

There is no output schema, so the description must convey what comes back; it does so by naming the preference categories, the privacy split, the 20-entry limit, and the expiry/cleanup behavior. Combined with the readOnly annotation and zero params, an agent has enough to call this correctly; only the exact return shape remains unspecified.

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 tool takes zero parameters, so the baseline is 4. The description correctly describes no inputs and instead explains what the (implicit) result set contains, which is the useful information here.

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 read operation over the caller's saved icebreak/match preferences and enumerates the categories read (WANT/AVOID, PROFILE/NEED/TEMP, rhythm/role/pause). It also names the mutating siblings (set_my_match_preference, revoke_my_match_preference, pause_need_icebreak), so an agent can separate this read from those writes. The acronym-heavy enumeration is somewhat opaque but the verb+resource is identifiable.

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?

Sibling routing is explicit: set_my_match_preference/revoke_my_match_preference change entries and pause_need_icebreak pauses a single need, which tells the agent when to pick those instead. It also notes the login prerequisite. There is no explicit statement of when NOT to call it or whether an empty result is normal, but the alternative mapping is clear.

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