Skip to main content
Glama

Save a spot at an address

save_spot

Saves a spot (a place that matters to the connected person, where Scout looks out for them) at an address they typed, with a kind: home, work, school, church, gym or other, and an optional name. The address must resolve to one confident, house-level match in their home city; when it does not, nothing is saved and the result lists the top suggestions with their lat and lon. Then ask the person which one they meant and call save_spot again with that suggestion's lat and lon (never coordinates from anywhere else). Ten spots per account; a spot already within a tenth of a mile is reported, not duplicated. Call this only when the person asks to save a place. Needs a connected account.

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": {
      "address": "<address>",
      "kind": "<kind>"
    },
    "name": "save_spot"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoOnly from a suggestion this tool returned, to confirm it.
lonNoOnly from a suggestion this tool returned, to confirm it.
kindYeshome, work, school, church, gym or other.
nameNoA nickname. Defaults to the kind (Home, Work, School, Church, Gym); required for other.
addressYesThe street address or place name they typed.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, open-world, non-idempotent write; the description adds far more: the single-confident-match requirement, that nothing is saved on failure, the suggestion payload with lat/lon, the ten-spot-per-account cap, and 0.1-mile dedupe reporting instead of duplicating. This is exactly the behavioral context annotations can't carry.

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?

One dense paragraph, front-loaded with what the tool does and immediately followed by the failure-mode procedure; no filler sentences. It is on the long side for scanning, but essentially every clause carries operational information.

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

Completeness5/5

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

For a write tool with a stateful retry loop, the description covers prerequisites, failure behavior, limits, and idempotency-by-dedupe; an output schema already exists so return shape details are correctly omitted. Nothing needed to invoke it correctly is missing.

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%, so the baseline is 3, but the description adds genuine meaning the schema's terse hints don't fully convey: it explains the save-then-confirm workflow that makes lat/lon valid only as echoes of a prior suggestion ('never coordinates from anywhere else'). Kind/name semantics largely duplicate the schema, hence not a 5.

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?

The description states a specific verb and resource ('Saves a spot ... at an address') and even disambiguates the domain concept ('a place that matters to the connected person, where Scout looks out for them'). The enumerated kinds and the optional name make it immediately distinguishable from siblings like add_errand or my_spots_and_routes.

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

Usage Guidelines5/5

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

It gives an explicit gate ('Call this only when the person asks to save a place') and a full recovery procedure for the failure path: when the address doesn't resolve, ask the person which suggestion they meant and call save_spot again with that suggestion's lat/lon. Prerequisite ('Needs a connected account') is also stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources