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

Annotations only say it is a write operation that is not read-only and not open-world; the description goes well beyond that, disclosing refusal conditions, the unit-counting semantics of min/max, and the key side effect that linking to a PARENT category detaches it from subcategories that already had it. That side-effect disclosure is exactly the kind of context a destructiveHint=false annotation cannot convey, and there is no contradiction with the annotations.

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?

Purpose is front-loaded and every sentence carries decision-relevant information (rules, refusals, side effects). It is, however, one dense block with nested parentheticals that make the refusal conditions harder to scan than a short list would.

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 6-parameter mutation with no output schema, the description covers what an agent needs to decide and call correctly: rules semantics, failure modes, and the parent-category cascade. The only real gap is that it says nothing about what comes back on success, which matters somewhat given there is no output schema to fall back on.

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 the baseline is 3, and the description earns above that by clarifying interactions the schema does not: that setting min makes the entry required, that required blocks the cashier from finishing the line, and that min/max count UNITS rather than choices when quantities are used. sortOrder is left entirely to the schema, keeping it from a 5.

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 first sentence states a specific verb and resource with scope: creating a modifier-ask link across every product in a category, framed as 'THIS is what puts it on the till.' That is enough to separate it from hub_unlink_modifier_from_category, but it never explicitly distinguishes itself from hub_update_category_modifier, which also sets min/max/required rules — the boundary an agent most needs is left implicit.

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 gives concrete when-not conditions (already inherited from a parent, already linked, unsatisfiable rules) and the 'link to the parent or the child, not both' routing rule, which is genuinely useful decision guidance. It does not name the alternative tools (update/unlink/get_category_modifiers) an agent should reach for in those cases, so routing is left to inference.

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