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

Annotations flag a write (readOnlyHint=false, destructiveHint=true), and the description adds real context beyond them: the write cannot touch the brand profile, unmentioned axes 'keep what they had' (partial overwrite), and it 'requires the act scope'. It also states the return payload, which no output schema provides. Missing only edge cases like re-writing the same axis.

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 routes with a WHEN clause, then closes with WHAT COMES BACK. No sentence is filler; even the 'Free; requires the act scope' fragment carries an actionable constraint.

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-nested-param write with no output schema, the description covers scope isolation, partial-update semantics, auth requirement, and return shape. An agent has everything needed to call it correctly and to know what it will and will not affect.

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% and the nested schema already defines 'lean' and 'strength' precisely, so the baseline is 3. The description still adds operational semantics not in the schema: omit axes with too few observations and send only axes that moved, which directly shapes what goes into the single 'axes' object.

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 ('Write the calibrated leans ... into the FOUNDER'S OWN voice profile') and immediately carves out what it is not ('the personal register, never the brand's'). The two-voices distinction lets an agent separate it from brand-voice siblings without opening any schema.

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 explicit timing ('after a round, once an axis has enough answers to read'), a batching rule ('one write per round, not one per pair'), and an exclusion rule ('leave out an axis with too few observations'). It stops short of naming sibling tools like get_voice_profile or record_voice_rule, but the when/when-not conditions are clear.

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