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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the lookup count is computed recursively over the entire include chain rather than just top-level mechanisms, and the 10-lookup threshold is the yardstick — that is real signal for interpreting results.

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 sentence with zero filler; the computed metric and threshold are front-loaded so the agent knows the output's shape of interest immediately.

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?

There is no output schema, so the description should say what comes back (the raw record? the numeric count? a pass/fail verdict?). It covers the core computation but leaves the response shape and error behavior undefined, which is a meaningful gap for an agent that needs to act on the result.

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 0%, so the description carries the parameter burden, and it only says 'for a domain' — which restates the obvious. It doesn't clarify whether a mail subdomain, apex, or URL is acceptable, nor what happens with invalid input. The single parameter with a 253-char constraint is otherwise self-evident, keeping this at a minimum-viable 3.

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 ('Read the SPF record for a domain') and goes further to say exactly what is computed: the DNS lookup count across the full include chain against the limit of 10. This cleanly separates it from the sibling build_spf_record, which constructs rather than inspects.

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?

The framing ('count the DNS lookup terms ... against the limit of 10') strongly implies diagnostic use when troubleshooting SPF lookup-limit failures, but no alternative is named and no when-not condition is given. An agent can infer the use case but must guess whether to reach for check_spf vs build_spf_record when auditing an existing record.

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