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

Annotations only declare it is a non-read-only, non-destructive write. The description adds genuinely useful behavior the annotations cannot: it requires the 'act' scope, is free, persists into Memory where the user can see and remove it, and is consumed downstream by morning marketing drafts, get_move, and get_voice_profile.

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?

Front-loads purpose, then WHEN, then constraints; no filler sentences. The middle sentence listing downstream consumers is a little dense and harder to parse than the rest, costing it the top score.

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-param persistence write with no output schema, it covers scope/auth, approval prerequisite, persistence/removal, and downstream effects. The only soft spot is the cryptic 'At most 12' whose unit is never stated.

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% (baseline 3), but the description adds constraints beyond the schema: the rule must be 'One sentence' and 'At most 12' (presumably words, though the unit is left implicit). This meaningfully narrows how to fill `text` relative to the 200-char cap.

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+resource with scope: 'Save one writing rule the person approved into their OWN voice, never the brand's.' The 'OWN voice, never the brand's' qualifier distinguishes it from siblings like record_claim, record_insight, and set_voice_axes.

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?

Explicit WHEN and a hard exclusion: 'only after they approve it in words' and 'Never record one they did not approve', including a concrete trigger (a yes to a rule proposed from an edit). It does not name an alternative tool for recording brand-level rules, so routing against siblings is left implicit.

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