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

Annotations already declare this is a non-destructive read (readOnlyHint true, destructiveHint false, openWorldHint true), so the bar is lower, and the description adds genuinely new behavior: a cost of 10 credits and the fact that IP blocklist and disposable email checks only apply on paid plans. That plan-gating detail is exactly the kind of context annotations can't convey. It stops short of describing what happens on free plans or rate/credit failure modes.

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?

One functional sentence carries nearly all the value, but it is preceded by a redundant 'Spam Detector: Spam Detector is a spam detection API' opening that restates the name and title twice. Every sentence should earn its place, and the first one doesn't.

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 an output schema present, the description needn't explain return values, and it covers the input expectation plus the credit cost and plan-tier limitations. The one relevant gap is that it doesn't tell the agent when passing an ip address has any effect, despite that being a schema parameter tied to paid features.

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 schema already documents text, email, and ip with examples, making 3 the baseline. The description reinforces text and email but conspicuously omits the ip parameter from its invocation guidance while separately mentioning 'IP blocklist' as a paid feature, which could leave the agent unsure whether ip is a usable input.

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?

The description states a specific verb and resource: it evaluates text submissions to determine whether content is likely spam. That distinguishes it well enough from generic siblings like ContentFilter or ProfanityFilter, though it never names an alternative explicitly. The leading 'Spam Detector: Spam Detector is...' repetition wastes the opening and adds nothing.

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 tells the agent what to pass ('a message body and an optional sender email') but gives no when-to-use or when-not-to-use guidance relative to sibling tools such as ContentFilter, ProfanityFilter, BotDetector, or DisposableEmailChecker. The paid-plan note on blocklist checks implies usage scoping but doesn't state it as a routing rule.

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