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

The description adds substantial behavior beyond the annotations: soft-delete semantics, idempotence across all edge cases, non-disclosure of which case occurred, explicit statement that version rows are never physically erased, and the post-delete resolution effects. These details are critical for an agent to trust and safely invoke the tool.

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?

The description is three sentences with no fluff, front-loaded with the core purpose, and every sentence adds meaningful behavioral detail. It is efficiently structured and easy to parse.

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 single-parameter tool with an output schema and strong annotations, the description covers all essential behavioral context: ownership, idempotence, non-disclosure, physical row retention, and post-delete resolution. No significant gaps remain.

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?

The input schema already provides 100% coverage for project_id, including its origin ('returned by house_specify for an authenticated (keyed) call'). The description adds context about ownership and house_ref effects, but does not need to elaborate on the parameter itself. Baseline 3 is appropriate given schema coverage.

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 opens with 'Soft-delete a durable house project you own,' clearly identifying the specific verb (soft-delete), resource (durable house project), and ownership constraint. It is immediately distinguishable from sibling tools like project_get, project_list, and project_versions.

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?

The description clearly states the tool applies to projects 'you own' and explains idempotent behavior for already-deleted, unknown, or not-owned IDs, setting expectations for when it can be safely invoked. It does not explicitly name alternatives, but the context is sufficient for a destructive single-resource operation.

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