Classification / property availability

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real domain behavior beyond that: user-defined properties only appear on an element when its classification makes them available, which explains the query's purpose. It doesn't state cost, limits, or pagination semantics beyond the schema's default, keeping it at 4.

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 purpose, then the two input/output contracts, then the mutation alternative. Dense but every clause carries information; the arrow-notation sentences are long but not padded.

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?

With no output schema, the description correctly supplies the return shapes, and it routes to get_classification_tree, get_property_ids_by_name and modify_property_definitions for adjacent steps. Complete enough to invoke correctly; only the items/properties mutual exclusivity is unaddressed.

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 3-baseline applies, but the description goes further by spelling out the response shape each mode produces ({item, properties:[...]} vs {property, availableForItems, items:[...]}), clarifying how the inputs map to output. It does not clarify whether items and properties can be combined, which is the main remaining ambiguity.

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 subject—property-definition availability versus classification items—in both directions, a resource no sibling touches (the nearest siblings are get_property_definitions and get_classification_tree, neither of which reports cross-availability). An agent can distinguish it immediately.

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 tells the agent to pass `items` for one direction and `properties` for the other, and it names the mutation path (modify_property_definitions {addAvailability}) plus the family it belongs to. It stops short of saying when this query is needed or that the two modes are mutually exclusive, so not a full 5.

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