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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new operational context: rate limiting per address, an error that reports seconds to wait, an error on invalid numbers, and precise semantics for each verdict including the important caveat that 'empty' is not a sign the number is safe. The distinction between 'restricted' (identity erased, reports remain) and 'unavailable' (lookup unreadable, says nothing) is exactly the kind of nuance annotations cannot carry.

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 purpose, then usage, then formats, then the verdict taxonomy, then error/rate-limit behavior — a sensible ordering with no filler sentences. It runs long mainly because the seven-way verdict enumeration is spelled out, which is defensible but costs some density.

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?

An output schema exists, so return values need not be explained, and the description still covers the failure modes (invalid number, rate limit, unreadable lookup) and the interpretive pitfalls of the verdict values. An agent has everything needed to decide to call it and to judge 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 100%, so the baseline is 3, but the description adds practical meaning: it restates accepted international and national formats with examples and notes that `country` is only needed for a national number outside the Netherlands. The per-verdict enumeration also ties output meaning back to the lookup rather than to any single parameter, so this is modestly above baseline.

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 ('Look up who is behind a phone number') plus the geographic scope (NL/BE/LU) and exactly what data comes back (community reports, spam/scam categories, trust verdict, registered business). The named data source ('Calmido phone directory') further pins it down, so an agent can distinguish it from the generic `fetch` and `search` siblings at a glance.

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 concrete triggering conditions: 'Use it whenever someone asks who called them, whether a number is safe, spam or a scam, or which company a number belongs to.' That is strong positive routing guidance, but there is no when-not clause and no explicit mention of the `search`/`fetch` siblings as alternatives, so it stops 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.