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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds real context beyond that: 'Private' signals data-sensitivity, and the explicit claim that it records only what another party stated (not invented clinical steps) frames its epistemic scope. The word 'records' sits in mild tension with readOnlyHint, but the leading 'read-only' framing keeps it from being a true contradiction.

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?

Three short sentences, front-loaded with the 'Private, read-only follow-up tracking' framing followed by purpose and boundary. No filler, though the prose is somewhat abstract rather than operational.

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?

An output schema exists, so return values need not be described, and annotations cover behavior. What remains missing is the input contract for the required 'items' parameter and any usage context, leaving the agent to infer both from the domain prose.

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% for the single required 'items' array, and the description only loosely hints at content via 'appointments, referrals, records and other stated next steps.' It never explains the item object shape or the array structure, so it only partially compensates for the coverage gap.

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 purpose: tracking follow-up items (appointments, referrals, records, stated next steps) so they don't disappear. It clearly differentiates the scope with the negative boundary 'does not invent clinical next steps.' However, it never concretely explains how 'track' behaves (surfacing vs. storing) given the ambiguous 'records' verb.

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?

There is no when-to-use guidance, no named alternatives among the many siblings (e.g. understand_need, next_action), and no conditions selecting this tool over others. The only directional statement is a scope exclusion ('does not invent clinical next steps'), which is a boundary, not routing advice.

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