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

Annotations cover the safety profile (idempotent=true, destructive=false, readOnly=false), so the description's job is narrower. It adds genuinely useful behavior: partial/per-item failure on wrong-typed entries ('fails its item') and an explicit boundary on what is mutated vs untouched (content blocks). It does not mention permission/auth requirements or the effect on unlisted fields.

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 compact sentences. The scope statement is front-loaded, followed by the failure rule and the explicit sibling hand-off. No filler.

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 the description covers scope, failure mode and the content alternative. What's thin is guidance on individual fields (title, relationshipIds) and multi-item semantics, though the schema enumerates them.

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%, so the description must carry parameter meaning, and it only partially does: it names visibility, tags and members but omits title and relationshipIds, and says nothing about campaignId or how the items array is applied. The parenthetical field list is a marginal help over the raw schema.

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 and resource ('Update typed/meta fields of Faction mnemons') and immediately scopes what is in-bounds (visibility, tags, members). It also explicitly separates itself from the same-named sibling update_mnemons_content, so an agent can distinguish it from the surrounding update_* / create_*_mnemon family.

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?

Gives the clear when-not condition plus the alternative: 'Does NOT modify content blocks — use update_mnemons_content for that.' It also states the failure condition for wrong-typed entries. It stops short of explaining when to pick this over the other type-specific updaters (update_npc_mnemons, update_lore_mnemons, etc.), which is left to inference.

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