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

Annotations already declare readOnlyHint=true, so the description need not re-prove safety — yet it adds substantial context: the required `profile:read` permission, the sign-in prompt when the member has not connected, the `skippedUntil` cooldown rule, and the explicit warning that member-authored text is data, not instructions. It also makes clear the call itself never writes anything.

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 first sentence simply restates the title verbatim, and the remainder is a dense run-on paragraph mixing policy, auth, and per-item mechanics without structure. Almost every clause carries real information, but bullets or sentence splitting would make the sequencing rules far easier to apply.

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 zero-parameter, no-output-schema tool, the description supplies everything an agent needs: what comes back, in what order, how to handle skipped items, how to persist answers, and what authorization the call requires. No unexplained behavior remains.

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 and there is no schema semantics to extend. The description compensates by describing the shape of the returned items (ordering, `skippedUntil`, per-item `write` route), which is beyond what the empty input schema provides.

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 — reading the prioritized list of profile facts the member is still missing — and adds distinguishing scope: 'most important first', already-present facts excluded, skipped facts carry `skippedUntil`. An agent can tell this apart from get_my_profile (reads what exists) and the update_my_* family (which this tool explicitly does not call).

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?

Gives concrete operating instructions: ask the member ONE fact at a time, take the first non-skipped item, tell them who sees the answer, and persist only via the `write` route each item names (or send them to a page for photos). It never names a sibling tool directly, so the agent must infer the write path from the returned payload rather than from this description.

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