delete_own_units

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

With no annotations, the description carries the full disclosure burden and does reasonably well: it declares permanence ("permanently kill"), warns that the engine "may refuse protected entities," and tells the agent to "observe later to verify," implying there is no reliable success acknowledgment. It omits partial-failure semantics (what happens when some IDs are valid and others are not) and permission requirements.

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?

Two short sentences with the destructive nature front-loaded, which is the right ordering. "Using the normal delete command" is filler that does not inform tool selection, and "observe later to verify" is terse to the point of being cryptic.

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 single-parameter, output-schema-less destructive tool, the definition covers the essential risks (permanence, engine refusal, need to verify afterward). It is still thin on what the call returns or how to confirm which IDs were actually deleted, which matters because the description itself admits success is not directly reported.

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 coverage is 0% for the single entity_ids array, so the description must compensate. It does partially: "selected currently owned Unit objects" tells the agent these IDs must be unit entities it currently owns, which the bare integer array does not convey. It adds no detail on batch limits, mixed-validity input, or ordering.

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?

"Permanently kill selected currently owned Unit objects" names a specific verb (kill/delete), a specific resource (Unit objects), and a scope qualifier (currently owned), which lets an agent distinguish it from siblings like delete_own_buildings or stop_units. It does not explicitly name a sibling to route away from, so it falls short of a 5.

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 vs when-not guidance. The description never contrasts this with non-destructive alternatives such as stop_units, move_units, or abandon_targets, nor does it state prerequisites beyond the implicit "currently owned." The only procedural hint is "using the normal delete command," which does not help an agent choose this tool.

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