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

Annotations already declare the safety profile (not read-only, idempotent, non-destructive, closed-world), so the bar is lowered. The description still adds real context beyond them: entries cannot be created here (the server provisions them when a character joins a party) and edit rights are governed by each entry's own permissions — a non-obvious authorization constraint. It omits batch semantics and partial-failure behavior for the up-to-50 item list.

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, purpose front-loaded, with the restriction and permission facts following. Nothing is padded, though the sentence fragments are choppy and the permissions clause could be tightened.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a batched mutation of up to 50 entries keyed by hex id or exact title, the description says nothing about atomicity, what happens when an entryId fails to resolve, or how visibility changes take effect — gaps the schema does not fill.

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 reported at 0%, and the nested item fields (title, tags, visibility, partyId, characterId, parentEntryId) are largely undocumented beyond two inline hints. The phrase 'typed/meta fields' does not map the agent to specific fields, does not explain the characterId/parentEntryId pairing, and does not mention the 1–50 item batch limit that is central to how this tool is called.

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?

States a specific verb (Update) and resource (typed/meta fields of Player mnemons) and adds a distinguishing fact — one per character in a party, auto-created by the server — which separates it from create_* mnemons tools. It does not name update_mnemons_content or the other update_*_mnemons siblings, so the agent must infer that this one covers only Player-type meta fields.

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 note that Player mnemons cannot be created usefully rules out the create_* family and hints that only meta fields are touched (body content presumably lives in update_mnemons_content), but that alternative is never named. With roughly a dozen sibling update_*_mnemons tools, the definition gives the agent only implied, not explicit, routing guidance.

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