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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral content: the hint vocabulary and the up-to-3 cap, which tells the agent what to expect back. The standalone 'Read-only' sentence is redundant with annotations rather than additive.

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?

A single dense paragraph, but front-loaded with the purpose and the hint list, then the input-format caveat. The redundant 'Read-only' tail is the only dispensable element, so it is efficient without being minimal.

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?

No output schema exists, and the description compensates by enumerating the possible hints and the cap, plus the judgment basis and required input form. An agent can call this and interpret the result without guessing, though the exact response shape is still only described informally.

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 100%, so the baseline is 3, but the description adds real meaning: campaign_id selects the campaign offer as the judgment basis and its absence falls back to program + autopilot offer, and body must be the rendered email rather than raw tokens.

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 action (quality hints / check) on a specific resource (an email draft) and grounds it in the familiar dashboard editor behavior. It is clearly distinguishable from siblings like preview_campaign_step, which it names as the upstream supplier of the input.

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 concrete usage context: pass the rendered email from preview_campaign_step, not {{tokens}}, and explains the fallback judgment basis when campaign_id is absent. It lacks an explicit 'when not to use' clause, so it falls 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.