abandon_targets

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

With no annotations at all, the description carries the full behavioral burden. It does add real value by disclosing what is preserved (stance and native autonomous reactions) and that UnitAI is not disabled, which implies units may re-acquire targets later, but it says nothing about reversibility, immediate side effects on unit state, or what the call returns.

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 tight sentences, front-loaded with the action and followed by the key negative constraint. Every clause carries information; there is no filler or repetition.

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 state-mutating tool with no annotations and no output schema, the description covers behavior reasonably but leaves the parameter contract and the observable result unexplained. It is adequate to recognize the tool's intent but not fully sufficient to invoke it confidently on a given entity_ids set.

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% for the single required parameter entity_ids, and the description never mentions it. It does not clarify whether the array accepts mixed unit types, all owned units, or how invalid or unowned IDs are handled, so meaning is added nowhere beyond the bare property name.

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 uses specific verbs and resources — 'Remove guard bindings, stop your units and clear their current and queued tasks' — so an agent knows exactly what operation occurs. It does not, however, name or contrast with nearby siblings such as stop_units or delete_own_units, leaving the boundary to be inferred.

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?

Usage is implied rather than stated: the tool is for releasing units from current engagements without turning off their AI. There is no explicit 'use this instead of stop_units when...' guidance or statement of preconditions, so the agent must reason about alternatives from the sibling list.

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