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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real value by enumerating what is inspected (trigger words by category/severity, ALL-CAPS, links/shorteners, offers, obfuscation, personalisation/opt-out, length) and by stating the scope limit. It does not disclose scoring thresholds or how weights combine, which keeps it from a 5.

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 that front-loads the verb, score scale, and timing before enumerating checks; every clause carries information. The mid-sentence list of checks is long but functional, and the scope caveat lands last where it is easy to miss.

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, the description compensates by stating the return shape ('each finding with how much it cost and how to fix it'), and it covers scope limits, inputs, and scoring model. An agent has everything needed to call it and interpret results.

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 both parameters are already fully documented, including the note that subject-line triggers weigh extra. The description's parenthetical '(subject hits weigh extra)' merely restates the schema, adding no new syntax or format guidance.

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, and output scale: 'Score a cold email's copy 0-100 for spam risk before it is sent.' It also draws a hard boundary ('Content only: it cannot see reputation or authentication'), which cleanly separates it from check_domain_reputation and check_deliverability among the siblings.

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?

'before it is sent' gives clear timing for when to invoke it, and the closing limitation tells the agent when this tool is insufficient. It stops short of naming the sibling tools to use for reputation/authentication checks, so the routing is implied rather than explicit.

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