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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds meaningful context beyond them: the character record persists and stays readable, `carry` moves specific parts to the successor, and the return value is described. The one gap is the null-successor case, which the schema permits but the description frames as if naming one is expected. The framing softens but does not contradict destructiveHint.

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 short sentences, front-loaded with the key semantic distinction (stamp, not deletion) before the successor requirement and return value. The aphoristic opening earns its place by disambiguating the destructive annotation. No filler sentences.

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 mutation with full schema coverage and annotations, the description covers the essentials: what persists, what is carried, and what is returned. But it is silent on the null-successor behavior and on reversibility via revive_character, both of which an agent would want before invoking a destructive tool. Adequate but with identifiable gaps.

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 100%, so the schema already documents all four parameters, making 3 the baseline. The description adds genuine meaning for `successor` (must be a living character of the same seat) but adds little for `carry` beyond the schema's "What moves to the successor." The framing of successor as something you "name" slightly undercuts the nullable optionality the schema exposes.

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 makes clear this marks a character as dead rather than removing it ("A death is a stamp, not a deletion: the sheet stays readable") and names the successor mechanic. The verb is expressed metaphorically rather than directly, so an agent must infer "mark as fallen/dead" from context, but the effect on the resource is unambiguous. It does not name a sibling it differs from.

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 successor must be "another of the same seat's living characters," which is a useful precondition for calling it. However, there is no guidance on when to choose this over revive_character or update_character_state, and no mention of whether the death can be undone. The neighboring revive_character tool makes this exclusion conspicuous.

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