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

Beyond the annotations, the description discloses the merge contract ('an axis with the same key gains the new values and keeps the old ones... labels and swatch colours are updated'), the authorization requirement (members only), per-call limits, and that changes take effect at once with no preview. These are exactly the facts an agent needs before mutating shared data. The gap is that it never states what comes back on success/failure or what happens to values already referenced by other products' variants when a label is relabelled.

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 verb and resource, then examples, then merge semantics, then operational facts — a clean information gradient. The em-dash example clause and the docs link add length, but every sentence carries distinct content; nothing is pure 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 non-idempotent, non-destructive write tool with no output schema and only two top-level parameters, the description covers purpose, merge behavior, limits, auth, and immediacy — enough for a correct call. What it omits is the response shape and any warning about downstream effects on products or variants that consume the axis, which would matter for a shared-resource mutation.

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 only 50%, so the description has work to do, and it does explain the semantic role of the 'key' field (matching an existing axis by key triggers merge rather than duplication), which is more than the schema's one-line note conveys. It also restates the maxItems limits in human terms and reinforces the projectId membership requirement. It does not clarify the string-vs-object value union, hex format, or how 'value' keys behave when defaulted, leaving part of the coverage gap unfilled.

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?

The description gives a specific verb and resource ('Create or extend the rikma's option axes') and backs it with concrete domain examples (Size S/M/L, Colour with hex). It implicitly separates this from variant-level tools by explaining that axes belong to the rikma and are shared by its products, but it never names the close sibling upsertProductVariantsTool or listRikmaProductOptionsTool, so the differentiation is inferred rather than stated.

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?

It supplies real operating constraints — members only, up to 3 axes per call, 30 values per axis, applied immediately — which shape how the tool is invoked. It does not say when to prefer this over upsertProductVariantsTool, or when to read state first with listRikmaProductOptionsTool, and it gives no exclusion conditions; usage is implied rather than prescribed.

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