Tie Ban Time Windows

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

Annotations only declare readOnlyHint=true; the description adds real behavioral context beyond that: it does not persist records, does not apply true solar time or additional DST correction, and rejects certain inputs outright. These are exactly the kind of operational facts annotations cannot convey. It does not describe the shape of the returned windows, but the safety/behavior profile is well covered.

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 content is valuable but delivered as one long semicolon-chained sentence mixing purpose, input precedence, rejection rules, exclusions, and persistence behavior. The key constraint is front-loaded, yet an agent must parse dense clauses to extract it; splitting into a purpose line plus a constraints line would improve it.

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 read-only preview tool with a nested oneOf subject object and no output schema, the description covers the essential call conditions: valid subject forms, time-source precedence, and rejection criteria. The remaining gaps are the roles of the optional fields and any indication of what the eight-window result contains, which matters given the absence of an output schema.

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?

With only 20% schema description coverage across five parameters, the description carries weight, and it does clarify the `subject` semantics (profile-or-record choice, prioritization of original civil birth time, no true solar time). However `notes`, `locale`, `question`, and `focus_area` receive no explanation in either the schema or the description, and the enum on `locale` is undocumented. Partial compensation only.

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 concrete computational output: eight complete 15-minute windows derived from the original recorded civil birth time, including the current and adjacent windows, cross-day boundaries, and boundary distances. It also scopes out what it is not (no traditional Tie Ban number-rising or texts), which helps separate it from the other divination.preview_* siblings. It stops short of a crisp one-line verb+resource statement, so it reads as dense rather than instantly scannable, but the purpose 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?

It gives an explicit input precondition — the subject must be the user's own profile or a chart record — and a hard rejection rule: direct four-pillars input lacking a verifiable civil time must be refused. That is meaningful when/when-not guidance. It never names a sibling alternative (e.g. another divination preview) for the rejected case, so routing is only partly covered.

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