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

Annotations already declare non-read-only, destructive and idempotent, but the description adds behavior the annotations cannot convey: a one-time confirmation code is sent to the reviewer's verified email, the agent must not retrieve that code on the reviewer's behalf, and the call does not itself approve the draft. These are meaningful operational and safety constraints beyond the structured hints.

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?

Six dense sentences, front-loaded with the positive case before the alternative. Nearly every clause carries information (scope, alternative, preconditions, side effects, prohibition), though the closing 'This does NOT approve the draft' partially echoes the earlier 'records no final approval'.

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 write tool with no output schema, the description covers preconditions, the side-effect channel (reviewer email code), and the non-approval outcome. It stops short of pointing to the follow-up confirmation sibling (e.g. helvabase_confirm_review) or describing what state the draft enters after the request.

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 coverage is 50% and the idempotencyKey is already documented in the schema, so the description's job is to compensate for the undocumented nested 'revision' object. 'This exact draft revision' plus the 'fresh source reads' precondition conveys that the revision must be pinned precisely and current, which adds real meaning, though it never explains the outputJobId/payloadHash pairing explicitly.

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: 'Request final approval review of this exact draft revision'. It immediately bounds scope ('not comments on an incomplete working document') and names the sibling it differs from (helvabase_export_dossier edition=review), so an agent can separate it from the export path without reading either 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?

Gives the explicit alternative and the condition selecting it ('For a working copy with declared gaps, use helvabase_export_dossier edition=review'), plus the preconditions for this tool: reviewer role, review scope, no unresolved blockers, fresh source reads. Both 'when to use' and 'when not to' are spelled out.

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