unload_garrison

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

No annotations exist, so the description carries the full behavioral burden. It does disclose genuinely useful traits beyond the schema: allied occupants are excluded from the default selection, native ejection/pathing restrictions still apply, and the caller should observe afterward to confirm the result. It omits what happens on partial failure, whether the holder must be owned or stationary, and whether the action is reversible.

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?

Tight and front-loaded: the core action comes first, then the default-selection rule, then caveats. The closing 'Observe to confirm' is terse to the point of being cryptic, but no sentence is wasted.

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 two-parameter mutation with no annotations and no output schema, the definition covers the happy path and the default-selection behavior adequately, but leaves error conditions, holder preconditions, and the outcome of the unload unexplained. It is functional but not sufficient for confident edge-case invocation.

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%, so the description must compensate for both parameters. It meaningfully clarifies entity_ids (omitted means all currently observed occupants, allies excluded), but holder_id is only defined indirectly through the 'your building, ship or mobile garrison holder' phrasing, with no indication of whether it accepts only owned entities or which ID namespace it uses.

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?

A specific verb (unload) applied to a concrete resource class (buildings, ships, mobile garrison holders), with 'your occupants' making the ownership scope explicit. An agent can tell this apart from unit-level siblings such as leave_turret or cancel_unit_packing without opening the schema.

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?

The description covers the one usage fork it knows about – omit entity_ids to unload everything observed – but gives no guidance on when to unload a subset versus the whole garrison, and names no alternative tool for related operations (e.g., leaving a turret, canceling packing). Usage is implied by the mutation verb rather than stated as a decision rule.

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