Skip to main content
Glama

Reload an extension

reload_extension

Refresh an unpacked Chrome extension to apply code changes, optionally reloading manifest.json, and get a cursor for log entries recorded since the refresh.

Instructions

Reload an unpacked Chrome extension so it picks up changes to its code. Pass reloadManifest if manifest.json changed too, and the result will say whether that looks like it worked. Only extensions that have called stdout() can be reloaded. Returns a cursor to pass as after to get the entries logged since the reload.

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": {
      "extension": "<extension>"
    },
    "name": "reload_extension"
  }
}

Input Schema

NameRequiredDescriptionDefault
browserNoThe browser to reload it in, by the name or ID that list_sources shows. Only needed when the extension is in more than one browser.
extensionYesThe extension to reload, by ID or exact name.
reloadManifestNoAlso read manifest.json again. Needs the current stdout-mcp library, with stdout() called when the service worker starts. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it discloses a real operational constraint (the extension must have called stdout()) plus the fact that the result reports whether the manifest re-read succeeded. It also explains the return value (a cursor for 'after'), which is valuable given there is no output schema. It does not describe failure modes or side effects when the reload itself does not take effect.

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?

Three sentences, front-loaded with the action and effect, then the conditional flag, then the precondition and return contract. No sentence is redundant and no padding is present.

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?

For a 3-parameter action tool with no annotations and no output schema, the description covers the precondition, the optional flag's purpose, and the return shape. Completeness would be higher if it stated what happens when the reload fails or when the extension is not running.

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 meaning beyond the schema by saying the result reports whether the manifest re-read 'looks like it worked', which tells the agent why to set reloadManifest and how to interpret the outcome. The browser parameter is left entirely to the schema.

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 ('Reload an unpacked Chrome extension') plus the reason for doing it ('so it picks up changes to its code'). That scope alone separates it from the log-oriented siblings such as get_logs and wait_for_log, so an agent can select it without opening the schema.

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?

Adds a condition for the optional flag ('Pass reloadManifest if manifest.json changed too') and a hard precondition ('Only extensions that have called stdout() can be reloaded'). It stops short of naming when to prefer a sibling, but the siblings' log-reading purpose makes an explicit exclusion largely unnecessary.

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