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

Annotations already declare readOnlyHint/idempotent/non-destructive, but the description adds substantial behavioral context beyond them: purgeEnabled gating (nothing is deleted while false), the 30-day grace period, the scan cap (capped), locked-project withholding (withheld is locked_rooms), permission-dependent empties, and an untrusted-content warning. This is rich disclosure the agent cannot get from structured fields.

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 and the key fields are front-loaded, and every clause carries information, but it arrives as one dense run-on block with parentheticals stacked inside it. It is informative yet hard to scan; a short lead plus a structured field list would serve better.

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 and zero parameters, the description carries the full burden and does so: it explains every return field, the semantics of dueNow/nextPurgeAt/freesBytes, graceDays, and the empty-result conditions. Nothing an agent needs to interpret the response is missing.

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?

Zero parameters, so the baseline is 4. The description instead documents the return buckets (kind, means, count, dueNow, nextPurgeAt, freesBytes, purgeEnabled, capped, storage, graceDays) in detail, which substitutes for the missing output schema, though that is context rather than input parameter meaning.

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 and scope: 'What is waiting to be removed for good in this workspace, by kind.' It enumerates the buckets and explicitly distinguishes itself from the sibling lnkdrp_list_deleted ('lists the items themselves'). An agent can tell exactly what this reports without opening any schema.

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 names the alternative explicitly and routes the agent: 'Counts and dates only; lnkdrp_list_deleted lists the items themselves.' It also states the caller context ('answers for a workspace owner or admin; for a member or viewer the buckets are empty'), which tells the agent when results may be empty. No explicit when-not, but the routing and role caveats are clear.

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