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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: 'soft-delete' tells the agent the data is not hard-purged, and it explains the idempotency mechanism (a repeat call with the same key returns the original result) rather than just asserting idempotence. It still omits permission requirements and whether/when a soft-deleted workspace can be restored.

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?

Three short sentences, no filler, with the operation and its destructive nature front-loaded before the confirm_name guard and the retry guarantee. Every clause carries actionable information.

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 destructive, 7-parameter mutation with no output schema and thin schema coverage, the description covers the two critical inputs but leaves gaps an agent would care about: what happens to the workspace's dependent content, whether the soft-delete is reversible and by what means, and the role of reason/brand_id. Adequate but not complete for the tool's complexity.

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 only 29% across 7 parameters, so the description must compensate and does so for the two riskiest: confirm_name (exact-match requirement, absent from the schema) and idempotency_key (retry semantics, beyond the schema's pattern/example). The remaining parameters (reason, brand_id, workspaceId, query) get no explanation in either place, leaving the compensation partial.

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 verb+resource ('Soft-delete a workspace') that cleanly separates it from sibling mutations like aidelly_update_workspace and aidelly_create_workspace. The 'soft' qualifier also hints at the operation's nature, though it does not explicitly name a sibling alternative such as archive.

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 a precondition ('confirm_name has to match the workspace name exactly') that tells the agent how to call it successfully, and the retry note implies when re-invocation is safe. It never says when to delete versus when to archive or update instead, nor what state the workspace must be in, so usage is only implied.

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