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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, and the description reinforces 'Changes nothing' while adding genuinely new behavior: required permissions ('Needs read and modify (trash: delete)') and per-call quota limits (50 Free / 500 paid). These are operational facts the annotations cannot express.

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?

Four dense sentences, front-loaded with the core action and effect, then workflow, then permissions and limits. Every sentence carries information, though the permission/quota sentence is tightly packed.

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 read-only preview of a 9-param, nested-schema tool, the description covers action, effect, routing to bulk_apply, owner-facing workflow, permissions and rate limits. An output schema exists so return-value detail is not required, yet the description still sketches the payload.

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?

With 78% schema coverage the schema does most of the work, but the description adds meaning beyond it: the explicit-vs-criteria selection modes, the 'oldest first' ordering, and the scan_from continuation implied by 'a sample and a confirm ref'. It stops short of documenting every field (e.g. the batch param).

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 and resource ('Selects the exact messages a bulk action would act on') plus the selection modes (explicit uids or criteria, oldest first) and the return shape (count, senders, sample, confirm ref for bulk_apply). This clearly separates it from bulk_apply (the executor) and search_messages (the uid source).

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?

Gives a clear workflow directive: use this before bulk_apply, then 'Show the preview to the owner.' The confirm ref tied to bulk_apply makes the pairing explicit. No explicit when-not-to-use or alternative, so it stops short of a 5.

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