Chickadee Bandit

Get household context

get_family_context

Read-onlyIdempotent

Read privacy-scoped shared family data. Keys: family.members, family.groups, family.calendar, family.tasks, family.locations, family.presence, and the per-member forms family.calendar.member:{id}, family.tasks.member:{id}, family.location.member:{id}. At most 12 unique keys per call; results are scoped to what the calling token's member is allowed to see. Location rows carry kind: "fix" (a position), "place" (at a safe zone — lat/lng are the ZONE's centre, zoneName says which) or "out" (between places, no position; since is when they left).

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": {
      "keys": "<keys>"
    },
    "name": "get_family_context"
  }
}

Input Schema

Name	Required	Description	Default
`keys`	Yes
`calendar_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 27, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the privacy-scoping model (token member's visibility), a hard 12-key cap, and the semantics of the returned location rows including the three `kind` values and what lat/lng mean for a 'place' vs 'out'. That is substantive behavioral context an agent could not infer from annotations alone.

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

Conciseness5/5

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

Front-loads the purpose, then the allowed keys, then the constraint, then return-shape notes. Dense and domain-specific with no filler; even the longer location sentence earns its place because 'place' meaning a zone centre is genuinely non-obvious.

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?

There is no output schema, and the description compensates by explaining the location row shape and the permission scoping. It leaves the return shape of the other keys (members, groups, tasks, presence) implicit and never explains calendar_days, so it is strong but not fully complete for a multi-key aggregate read.

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 0%, so the description must carry the load; it does so for `keys` by enumerating allowed values, explaining the per-member `family.X.member:{id}` forms, and tying key choice to the 12-key limit. However `calendar_days` (1-365) is never mentioned, leaving one of two parameters undefined in both schema and description.

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?

States a specific verb and resource ('Read privacy-scoped shared family data') and then enumerates the exact key namespace, distinguishing it from the app/activity/conversation siblings. An agent can tell immediately this is the household-read tool.

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?

Gives the operational constraint (at most 12 unique keys per call) and the authorization context (results scoped to the calling token's member). It does not explicitly contrast against siblings like get_activity_feed, but those are different domains so no routing ambiguity remains.

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

All Chickadee Bandit 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?