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

readOnlyHint and destructiveHint already cover the safe read nature. The description adds behavioral context by emphasizing 'static reference data', 'no birth data required,' and listing exactly which data fields the call returns. This adds practical meaning beyond the annotations, though still not a comprehensive account of output-shape.

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?

Two sentences, tightly packed: the first states the core action and returned fields; the second clarifies scope and prerequisites. No filler, no waste.

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 a simple read-only, 1-param endpoint, this is complete: it states what to pass, what to get back, and the explicit applicable scope. The lang/compact params are already fully documented by schema, and the description enumerates the returned fields directly.

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%; the input schema already documents number, lang, and compact in enough detail. The description repeats the number range ('1 to 64`) and doesn't add semantic guidance for lang or compact, so the description does beyond a already at the baseline—it doesn't add meaning beyond the schema.

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 states the exact verb-resource pair: 'Look up the static reference data for a Human Design gate by its number from 1 to 64' and then names the returned fields—keynote, center, hexagram, channal gates. This clearly distinguishes it from the siblings like post_human_design_gates and other birth-data-requiring endpoints.

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 purpose is clearly delimitated: 'pure reference endpoint with no birth data required.' This conveys when to use it (static gate reference) versus chartPerson/calculation endpoints, but it doesn't name those alternatives explicitly. It provides clear context with no exclusion, otherwise scoring lower than 5.

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