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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial context beyond them: the exact evidence sources consulted (SPF/DKIM/DMARC, display name vs. domain, Reply-To, link text vs. destination, prior payee), the three-way verdict shape, privacy handling ('processed in memory and not stored'), and the cost/auth profile ('Free, no API key'). That is the kind of detail that lets an agent anticipate both the output and the side effects.

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?

Front-loaded with the triggering condition and every sentence carries information—checks, inputs, verdicts, and the no-pay instruction. It is a single dense block of roughly 150 words; light structuring of inputs vs. checks vs. outputs would read faster, but there is no filler to cut.

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 an 11-parameter read-only screening tool, the description covers the trigger, the meaningful inputs, the analysis performed, the return verdicts, privacy, and the required agent action on decline. An output schema exists and the return values are still summarized in prose, so nothing an agent needs to invoke or act on the result is missing.

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 already 91%, so the schema carries most of the load; the description nonetheless adds meaning by explaining what to pass ('raw headers if you have them, the From line, subject and body (or body_html)') and why (headers enable SPF/DKIM/DMARC, body_html enables link-text comparison). It doesn't cover network, previous_pay_to, or expected_sender_domain semantics in the description, which prevents a 5.

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_payment_request' / check a payment request before paying) and immediately scopes it to messages that ask for payment. The listed checks (sender authenticity, domain/brand imitation, payee match, pressure language) make it clearly distinct from siblings like payee_decide, screen_address, and verify_payment_requirements.

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 ('call this before paying because an email, invoice or chat message asked you to') and an explicit follow-up rule ('on decline, do not pay from this message; confirm through a channel you already trust'). It doesn't name when to skip this tool or which sibling to use instead, which keeps it short of a 5.

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