SendGuard

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

Goes beyond the annotations by disclosing free-tier quota ('3 free checks per day per IP'), the API-key gate for higher limits, the exact verdict set, and the reason-code categories that drive the decision. Annotations already establish idempotent/non-destructive, and 'Does not send email' reinforces rather than contradicts them. Missing only persistence/logging behavior for the submitted content.

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?

Three tight sentences, front-loaded with the action and its boundary, then outputs, then auth/quota limits. No filler and no restatement of the title.

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 14-parameter, read-non-destructive evaluation tool with full schema coverage, an output schema, and safety annotations, the description supplies everything else an agent needs: what it returns, what it does not do, and the unauthenticated rate limit.

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% and all 14 parameters carry inline descriptions with examples (intent, policy, recipient_source, etc.), so the schema does the heavy lifting. The description adds nothing parameter-level beyond implying the API-key context of agent_id/workspace_id. Baseline 3 is appropriate.

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 ('Check an AI-written email') and immediately bounds the action with 'Does not send email', so an agent knows this is a verdict tool rather than a send tool. The returned decision vocabulary (allow, delay, requires_approval, block) further pins down scope. No siblings exist, so differentiation is moot but the purpose is unambiguous.

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?

'Check ... before sending' gives explicit timing and workflow context for invocation. It doesn't state when NOT to call it or name alternatives, but with no sibling tools there is no real alternative to route away from. Clear context without exclusions lands at 4.

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