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

Annotations only say destructive/non-read-only; the description goes well beyond by disclosing whole-value replacement, the list-replacement rule, durability across re-learning, the reset escape hatch, no-AI raw storage, and all-or-nothing atomicity of a call. Those are precisely the destructive-behavior details an agent needs before invoking.

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-loaded with purpose and trigger examples, then constraints. It is dense but nearly every sentence carries a distinct operational rule; only the repeated reset/wording around durability is slightly redundant.

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 the high-risk semantics for a destructive single-parameter mutation: atomicity, replacement semantics, persistence, reset, and scope limits. Only the return value/confirmation shape is left unstated, which is a minor gap absent an output 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 coverage is 100%, so field types and the voice_signature word vocabulary are already documented. The description adds the semantic that matters: each edit replaces the entire field value, so lists must be sent complete. It does not re-explain per-field enum values, which is fine since the schema does.

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?

Specific verb + resource + scope: changes the caller's own personal writing voice, equivalent to Settings > Voice. It explicitly carves out what it is not (a teammate's or a client workspace's voice) and routes workspace positioning to update_brand.

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 concrete trigger utterances the agent can pattern-match against ("I never use the word synergy", "I work with Dana now") plus named alternatives: get_brand_voice to read current state and update_brand for workspace-level positioning.

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