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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered structurally; the description's real addition is the explicit promise that it 'Runs no check on any domain' and that it returns study-sourced cost figures and full URLs. Beyond that it doesn't describe response shape or size (no output schema exists to cover it), and the cost-figure claim is stated without any caveat about how those numbers should be read. Useful context, but not rich disclosure beyond the annotations.

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?

Purpose is front-loaded in the opening clause, and the closing sentence carries the invocation rule and the no-checks disclaimer where an agent will see it last before acting. It is one very long sentence whose middle clauses enumerate distinct returned artifacts, each arguably earning place, though the SURBL-vs-Google cost example is illustrative padding that could be trimmed.

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 carries the full burden of explaining returns, and it does so concretely: ordered checks with associated tools, study-measured costs, guides and studies with URLs, fix evidence, operator notes, and the scenario list when called bare. For a zero-required-parameter, read-only lookup tool, an agent has everything needed to call it correctly and to anticipate the response.

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 description coverage is 100%, so the baseline is 3, but the description adds two things the schema cannot: that the symptom should be phrased in the person's own words (lowering the bar to natural language) and that omitting both parameters returns the scenario list rather than erroring. That fallback behavior, given both parameters are optional, is genuine meaning beyond the schema.

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 ('Returns WarmInboxes' diagnostic playbook for a cold email problem') and enumerates the artifact's contents — ordered checks with tools, study-measured costs, guides with URLs, fix evidence, operator notes. It also distinguishes itself from the many check_* siblings by stating 'Runs no check on any domain,' so an agent can separate it from check_surbl or check_blacklist without reading the 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 explicit invocation modes: pass a symptom in the person's words, or a scenario id, and states the no-argument fallback ('with neither it lists the scenarios'). It also carves out the negative case (it performs no checks), which implicitly routes deterministic checks to the check_* tools. It stops short of naming a specific alternative such as burned_inbox_guidance or spamhaus_dbl_guidance, so sibling selection between the guidance tools is still left partly to inference.

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