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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful non-annotation context — the scoring scale orientation and the returned components (risk level, per-control sub-scores, plain-language summary) — but says nothing about cache behavior despite exposing force_refresh, nor about latency or what happens on an unresolvable domain. That is a modest contribution beyond structured data, so a 3.

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 sentences, correctly front-loaded: what it computes, what it returns, when to use it. Efficient. Minor redundancy in restating 'composite spoofability/poofing risk score' in both the first and third sentences, which costs a fraction of a point rather than the whole.

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 burden of describing return values, and it does so adequately (numeric score, risk level band, sub-scores, summary). For a 3-parameter read-only tool that is nearly sufficient; only cache/refresh behavior and failure modes are unaddressed.

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 domain, format and force_refresh are already documented in the schema, and the enum values for format are listed there. The description adds no semantics beyond that — notably it does not explain what 'compact' omits or how the cache is keyed. 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 ('Compute a composite email spoofability risk score') and pins down the scale and direction (0-100, higher = more spoofable) plus the inputs consumed (SPF trust surface, DMARC enforcement, DKIM coverage). The word 'composite' implicitly separates it from per-record checks like check_spf/check_dmarc in the sibling list, but no sibling is named, so differentiation is inferred rather than stated.

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 an explicit trigger: 'Use when asked how easy it is to spoof email from a domain, or for a composite spoofing risk score.' That is clear context for selection. It stops short of exclusions — it never says to use the individual check_* tools instead when only one control is of interest, nor does it mention the batch equivalents.

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