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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds the crucial substance: the battle collapses into its summary and can 'never move again,' making the irreversibility concrete. It also discloses the GM-only authorization requirement, which annotations do not express. It omits edge behavior such as what happens if the battle is already ended, keeping it short of a 5.

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 terse sentences, with the state-changing consequence front-loaded before the permission note and the return value. The opening 'Call it.' is filler that does no work and reads as an instruction rather than a description, which is the main blemish on an otherwise tight entry.

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 destructive terminal operation with no output schema, the description covers the essential traits: the resulting state, permanence, authorization, and a one-line return note. Missing only re-invocation behavior and any note on whether the summary is recoverable, which are minor for a simple, fully schema-documented tool.

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%, with both 'battle' (its id) and 'campaign' (slug or id) already documented in the schema. The description says nothing about either parameter, adding no syntax or format meaning beyond the structured fields, so the baseline 3 applies.

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 conveys a concrete verb-effect pair: the battle 'becomes its summary and never moves again,' which is a specific and unusual way of saying the battle is terminated and frozen. Together with the title 'End a battle' an agent can identify the operation. It doesn't explicitly name how it differs from update_battle or create_battle, but the terminal-state framing does distinguish it implicitly.

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?

'Call it.' gives no condition for when to invoke this versus update_battle or other battle lifecycle tools, and there are no exclusions beyond the 'GM only' permission gate. The GM-only note is a real usage constraint but not routing guidance, so an agent still has to infer that this is the final step rather than a mid-battle edit.

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