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

Annotations already cover the safety profile (not read-only, not destructive, idempotent), and the description adds beyond that: the pin cap ('up to 6'), the fact that exclusions are permanent ('never used as examples'), and that each call is a single undoable change. It doesn't state permission or workspace requirements beyond the schema.

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?

Purpose and the enumeration of actions are front-loaded, and the undo guarantee is a well-placed short follow-up sentence. The first sentence is long and list-heavy, but nothing is wasted.

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?

Covers all seven optional parameters' effects at the operation level and, since an output schema exists, needn't describe return values. Minor gap: no guidance on combining actions in one call beyond the reset-precedence note already in the schema.

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% and the schema already spells out each parameter's meaning (including 'never used as examples' and reset precedence), so the description mostly repeats it. Baseline 3 applies when the schema does the heavy lifting.

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 set (pin/unpin/exclude/restore/reset) on a specific resource (the writer's own example posts) and explains the effect ('show how they sound'). It also routes to list_voice_examples as the id source, distinguishing it from the read-only sibling.

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 an explicit trigger — 'when the writer asks you to' — and enumerates the five sub-actions with their intent, plus where ids come from. It stops short of naming when NOT to use it versus adjacent tools like add_voice_material or update_voice_stances.

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