Skip to main content
Glama

set_geolocation

Idempotent

Override browser geolocation with fixed coordinates for location-based pages without a permission prompt; reset restores the native position.

Instructions

Override navigator.geolocation with fixed coordinates (page-level patch). reset restores native. For location-based pages (store locators, delivery zones): it answers without a permission prompt, and a reload or navigation drops it, so call it after navigate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
resetNoRestore the real position and stop overriding
tab_idNoTarget tab; omitted = last tab navigated in this session, else the active one
accuracyNoMeters
latitudeNoDecimal degrees, -90 to 90
longitudeNoDecimal degrees, -180 to 180

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.10.0
    • addedInput schema / properties / latitude / description
      Added value: +"Decimal degrees, -90 to 90"
    • addedInput schema / properties / longitude / description
      Added value: +"Decimal degrees, -180 to 180"
    • addedInput schema / properties / reset / description
      Added value: +"Restore the real position and stop overriding"
    • addedInput schema / properties / tab_id / description
      Added value: +"Target tab; omitted = last tab navigated in this session, else the active one"
  2. First observedv1.8.0

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond annotations by disclosing that it answers without a permission prompt and that a reload or navigation drops the override. The annotations cover the safety profile, and the description adds real behavioral context, though return format is not described.

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?

Two compact sentences: core behavior first, then the critical ordering caveat. Zero filler, and the most actionable info (call after navigate) is front-loaded.

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?

Covers purpose, lifecycle, and ordering for a 5-param tool with full schema coverage and no output schema. The permission-bypass and reload caveats fill the main gaps; only return-value format is omitted, which is minor here.

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 baseline is 3, and the description adds meaningful semantics on top: 'reset restores native' and that the override is page-level and lost on navigation, which affects how latitude/longitude/tab_id should be used. It does not restate each parameter but adds the lifecycle insight.

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: overriding navigator.geolocation with fixed coordinates. The parenthetical 'page-level patch' clarifies scope, and no sibling among ~60 tools covers geolocation, so it is unambiguous.

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 a concrete use case (store locators, delivery zones) and an explicit ordering instruction ('call it after navigate'), which is genuine when-to-use guidance. It lacks explicit when-not-to-use guidance or named alternatives, though no direct alternative exists.

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