API Tool Calls

Run Loop Maker

make_run_loop

Read-onlyIdempotent

Make walking/running loops that start and end at one point, each within 3% of the target distance. Returns Google Maps links and an encoded polyline. Routes and map data © OpenStreetMap contributors (ODbL); each result credits the routing service that made it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`via`	No
`count`	No
`start`	Yes
`stops`	No
`prefer`	No
`direction`	No		any
`avoid_crime`	No	Steer round blocks with more reported crime than the start (city police reports, last 12 months; San Francisco and Seattle for now). Not a guarantee.
`distance_km`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 7, 2026

addedInput schema / properties / avoid_crime

Added value: +{
+  "default": false,
+  "description": "Steer round blocks with more reported crime than the start (city police reports, last 12 months; San Francisco and Seattle for now). Not a guarantee.",
+  "type": "boolean"
+}

AddedOct 6, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world status, so the bar is lower. The description adds real value: the 3% distance tolerance, the return payload (Google Maps links + encoded polyline), and the ODbL attribution requirement, which hints at reliance on external routing data.

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?

Three sentences, front-loaded with the core behavior and constraint, no padding. The closing attribution sentence is compliance boilerplate but legitimately informative about data provenance.

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

Completeness2/5

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

Return format is covered (links + polyline, so no output schema is needed), but for an eight-parameter route generator the description says nothing about how via/stops/prefer/direction shape the loop. An agent must reverse-engineer the route-building semantics from bare schemas.

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

Parameters2/5

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

Eight parameters with only 13% schema description coverage, and the description names no parameter at all. It implicitly constrains 'distance_km' via the 3% tolerance and 'start' via the start/end-at-one-point rule, but leaves 'via', 'stops', 'prefer', and 'direction' entirely to the schema, which does not document them.

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?

Specific verb and resource: 'Make walking/running loops that start and end at one point,' plus a precise behavioral constraint (each loop within 3% of target distance). No sibling tool performs route generation, so the tool is unambiguous against the surrounding calculator/citation tools.

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

Usage Guidelines3/5

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

The activity type (walking/running) implies the use case, but there is no explicit when-to-use, when-not-to-use, or alternative routing mode. Usage is inferable rather than stated.

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

All API Tool Calls tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?