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

Annotations already declare destructiveHint=true and openWorldHint=false; the description adds context the annotations cannot carry: it is free, requires the 'act' scope, and returns every axis on record plus top moves. It also clarifies merge behavior ('Send only the axes that moved; the rest keep what they had'), which softens but does not fully explain the destructive overwrite of a previously recorded lean on a re-sent 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-loaded with the core action, then organized under WHEN and WHAT COMES BACK headers, which reads efficiently. The second sentence largely restates the first sentence's brand-vs-founder exclusion, costing a line without new information.

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 destructive, nested-parameter mutation with no output schema, the definition covers timing, batching, scope, cost, and return contents — enough to call it correctly. Gaps remain on what happens when an axis id is unknown or a lean is overwritten, and on any error/partial-failure behavior.

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 axes object already documents lean ('a'/'b' pole) and strength (0.5–1 share of observations). The description adds selection semantics — send only moved axes, omit under-observed ones — but no additional detail about the shape or keying of the axes object beyond the schema, so the baseline 3 holds.

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: 'write the calibrated leans from a voice round into the FOUNDER'S OWN voice profile.' It immediately bounds the resource by contrast — 'never the brand's' — so an agent can distinguish it from any brand-voice write path without opening a 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?

Explicit timing ('after a round, once an axis has enough answers to read') plus exclusions ('leave out an axis with too few observations: that is not a lean') and batching rules ('one write per round, not one per pair'). It does not name a concrete alternative tool for the brand-voice case or for recording individual rules, so the routing half of the guidance is left implicit.

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