Reconcile absences

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

Beyond the annotations (destructive/idempotent/not-read-only), the description discloses non-obvious transactional behavior: entries are validated and resolved before any write, the run is all-or-nothing ('one faulty entry leaves the whole run without effect'), and it must execute inside an open unit of work. These are exactly the traits an agent needs to call it safely and are not derivable from the structured fields.

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 tight sentences, front-loaded with the purpose, then atomicity, then the transaction precondition. No wasted words, though the dashes make it slightly dense.

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 destructive, nested-schema tool with an output schema (so return values need not be explained), the description covers purpose, atomicity, and the transaction requirement. It could be more explicit that mirroring replaces/clears existing absences in the window, but the schema's 'an empty array clears the window' partly covers that.

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 100%, so the nested entry/timeWindow/periods semantics are already fully documented by the schema, and the description adds no field-level meaning beyond 'many people and teams' and 'every entry'. Baseline 3 is appropriate when the schema carries the parameter burden.

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 gives a specific verb ('mirrors'/reconcile) and resource (absences of many people and teams), plus the batch framing ('in one call - the daily run of a foreign system'). An agent can distinguish it from the singular rillsoft_resource_absence_list by the bulk/mirror semantics, though no sibling is named explicitly.

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 clear context for when this applies ('the daily run of a foreign system') and a hard precondition ('Inside an open unit of work only'). It does not, however, name an alternative or state an explicit when-not, so it stops short of the top band.

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