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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is carried structurally. The description adds nothing beyond that: it does not say whether removing an override reverts the property to its inherited/global definition, whether children or values are affected, or whether the operation can be undone. With annotations covering the basics, this is a marginal addition rather than a contradiction.

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?

It is short, but the brevity is not earned — the single line is a pipe-delimited keyword dump rather than a front-loaded statement of purpose. The most decision-relevant information (that this deletes an override and what that implies) is absent while low-value search terms are included.

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?

Contextually this is actually the strongest dimension: with 100% schema coverage and annotations that flag the tool as destructive, the description does not need to explain parameters or safety. The residual gap is that an agent gets no statement of effect (override removed, definition reverts), but the structured metadata prevents this from being a fatal omission. Score kept at 4 only because the structured fields do most of the work; the prose itself is near-empty and a short sentence on the delete semantics would have made this a 5.

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 description coverage is 100%: def_id and scope_id are both documented as identifying the override row and its scope. The description contributes no additional meaning about these parameters. Per the high-coverage baseline, a 3 is appropriate.

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 is a namespace path plus a keyword list ("Ontologie: onto/property_def/delete_override | EN: property, field, schema, property set, definition") that essentially restates the tool name and title. The word "delete_override" signals removal of an override definition, but there is no explicit verb+resource sentence explaining what is deleted. It does not differentiate from onto_property_def_update or onto_property_def_create.

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?

There is no guidance on when to use this tool, when not to, or which sibling to prefer. An agent has many neighbouring tools (onto_property_def_update, onto_property_def_create, onto_object_delete_property) and the description gives no basis for choosing. The EN keyword list is search bait, not usage guidance.

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