Mobile number numerology

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), and the description adds genuinely new operational facts: the call costs 10 credits (Tier 1), the driver/conductor section only appears when a birth date is sent, and the response explains which convention was chosen over pair-meaning tables and Cantonese homophones. Those are behaviors no structured field discloses.

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?

The core sentence is a single long clause chain dense with domain jargon ('Cheiro's compound reading', 'driver and conductor', 'both conventions'), which slows a reader trying to skim. The bracketed Group/Endpoint/Required/Cost block is useful but appears after the payload rather than as a lead-in, and the convention-rationale sentence is arguably output detail. Nothing is pure filler, but it is not front-loaded for fast scanning.

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 documented, and annotations cover safety; what remains is scope, cost, and parameter behavior, all of which the description addresses. The only real gap is routing guidance against the many sibling numerology tools. For a two-parameter read-only computation this is close to complete.

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 only 50%, and the undocumented parameter is 'date'; the description supplies its meaning by tying it to birth-date-driven driver and conductor compatibility computed 'under both conventions'. Combined with the schema's own note on omitting the country code from 'number', an agent has enough to fill both fields correctly.

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?

The description names a concrete verb-set and resource: digit total and reduction of a phone number, Cheiro compound reading, driver/conductor compatibility, and adjacent-pair harmony. That is far more specific than the title, and the endpoint line reinforces it. It does not explicitly separate itself from the house-number and vehicle-number siblings, but the 'phone number' framing makes the resource unambiguous.

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?

Usage is only implied by scope: an agent can infer this is the tool for phone numbers rather than houses or vehicles. There is no stated when-not, no named alternative for related readings, and no guidance on when to supply a birth date versus calling without one. The conditional 'when a birth date is sent' is the closest thing to a selection rule.

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