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

Beyond the annotations (which only say readOnly=false, idempotent=false, destructive=false), the description discloses that the change happens in place, that the concentrate scales while finishing alcohol fills the remainder, that missing ethanol is pulled from the catalog, and that the result is capped at the concentrate's own strength. These are material side effects an agent could not infer from structured fields.

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 use case, then densely packed constraints in short sentences. A few fragments ('In place.', 'Capped at the concentrate's own strength.') read tersely and their referents are slightly implicit, but no sentence is filler.

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 mutating, non-idempotent tool with no output schema and fully documented params, the description covers trigger, side effects, material sourcing, and the strength cap. It stops short of saying what happens when the target exceeds the concentrate's strength (error vs clamp) or whether undo_last_change applies, which are the remaining ambiguities.

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 baseline is 3. The description mentions the totalGrams omission rule and the percentage semantics, but that guidance is already present in the schema property descriptions (omit to keep current weight, 20 means 20%), so it adds little beyond structured data.

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 ('change a formula's concentration or its finished weight'), names the concrete UI surface ('the app's Scale sheet'), and explicitly separates itself from dilution behavior by saying to recompose rather than add solvent to an existing mixture. An agent can pick it apart from update_formula or make_dilution 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?

Opens with an explicit trigger ('Use this when the user wants to change...'), then gives conditional handling: concentration-only requests omit totalGrams, while weight changes supply it. It also warns off a plausible wrong pathway ('never infer it by dividing existing grams by the concentration') and distinguishes recomposition from solvent addition.

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