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

Annotations already establish read-only, idempotent, non-destructive behavior, but the description adds important semantics beyond that: summaries are rewritten only when indicators change, staleness fields must be checked, and the score is a risk score where lower is healthier. It also warns that a rising score means deterioration, preventing a likely misinterpretation.

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 description is front-loaded with the core purpose, then adds freshness guidance and score interpretation in a compact sequence. Every sentence earns its place by either distinguishing the tool, preventing stale quoting, or preventing score misinterpretation.

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 carries the burden of explaining return content and does so effectively: it names the score, regime, `stale`, and `ageDays`, explains when the summary changes, and defines the score scale and direction. This is complete enough for correct selection and interpretation.

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 has zero parameters, so there is no input parameter semantics to explain; the baseline for this situation is 4. The description still adds meaning about return fields like `stale`, `ageDays`, score, and regime, which is useful even though it is not strictly input-parameter documentation.

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 exactly what the tool returns: the latest written Zensei Index summary with its score and regime. It distinguishes itself from the sibling zensei_index_today by telling the agent to prefer that tool for the current number.

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 explicit routing guidance: use this for the written summary, check `stale` and `ageDays` before quoting it as today's view, and prefer zensei_index_today for the current number. This is a clear when-to-use/when-to-prefer-alternative instruction.

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