Human Design

Compare Two Saved People

compare_charts

Read-onlyIdempotent

Compare two saved people's Human Design charts for relationship dynamics.

Computes electromagnetic, companionship, compromise and dominance channels, composite type and authority, center dynamics, connection theme, profile compatibility, and bridging gates: the gates each person supplies that close the other's split definition, and the gates neither holds that would close the composite's split. The tool for any question about how two people fit; it also renders the connection view the user sees.

Both people must be saved (or 'me'). Someone the user describes but has not saved yet is stored first with save_person.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "person_a": "<person_a>",
      "person_b": "<person_b>"
    },
    "name": "compare_charts"
  }
}

Input Schema

Name	Required	Description	Default
`person_a`	Yes	The first person's full name exactly as saved (a partial name fails), or 'me' for the account holder
`person_b`	Yes	The second person's full name exactly as saved (a partial name fails), or 'me' for the account holder

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 9, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds value beyond that: it discloses that the tool 'renders the connection view the user sees' (a visible UI side effect) and that unsaved people must be persisted via save_person before use, which is behavioral context the annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose in the first sentence, followed by precondition and alternative. The middle paragraph is a dense enumeration of computed outputs that is somewhat redundant given an output schema exists, but it is informative rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the return values need not be restated, yet the description covers what the comparison produces, the exact-name requirement, the 'me' alias, and the save_person fallback. What is missing is failure behavior (e.g. what happens when a name does not resolve), which an agent would need for error recovery.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself spells out that the name must match exactly (partial name fails) and that 'me' is accepted, so the baseline would be 3. The description reinforces the operative constraint ('Both people must be saved (or "me")'), adding a precondition the schema's per-field text only implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('compare two saved people's Human Design charts') and enumerates the concrete computations (electromagnetic, companionship, compromise, dominance channels, composite type/authority, bridging gates). It is clearly distinguishable from siblings like get_person_design (one person) and analyse_group (groups).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the use case broadly and confidently ('The tool for any question about how two people fit') and gives a real precondition plus a route for the failing case: both people must already be saved, otherwise store them first with save_person. It does not, however, explicitly contrast against neighbours such as compare_birth_times or get_person_design.

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

All Human Design tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?