EXZA Remote

Start commander search

exza_start_commander_search

Begin a bounded asynchronous filename/content search and return a search-session ID; no files are edited. Use exza_get_commander_search_results for its pages and search_stop to discard the session. Requires account-bound computer:write OAuth and any prompted local owner approval.

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": {
      "query": "<query>"
    },
    "name": "exza_start_commander_search"
  }
}

Input Schema

Name	Required	Description
`mode`	No	Search filename (name) or bounded text contents (content).
`path`	No	Explicit path inside the scope for this tool; no symlink traversal where prohibited.
`query`	Yes	Literal name or content search query, restricted to the authorized area.
`maxResults`	No	Maximum results to search; server bounds still apply.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotent=false; the description reconciles this by stating 'no files are edited' while implying session state is created, and adds auth requirements (account-bound computer:write OAuth) plus a local owner approval prompt. The word 'bounded' hints at server-side limits but is not quantified.

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?

A single front-loaded sentence establishes the action, asynchrony and return value, followed by a second sentence covering follow-up tools and prerequisites. No filler; 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 session-starting tool with no output schema, the description supplies the key return value (session ID), the follow-up tools needed to consume or discard it, and the permission prerequisites. An agent has everything needed to call it and know what to do next.

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

Parameters3/5

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

Schema description coverage is 100%, so each of the four parameters is already documented with enum, path, query and maxResults semantics. The description only restates the name/content distinction and the bounded-results notion, adding no syntax or format detail beyond 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 ('Begin a bounded asynchronous filename/content search'), names its return value ('search-session ID'), and explicitly distinguishes itself from the results-fetching and stop siblings. The mode distinction (name vs content) maps to the schema enum and reinforces scope.

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?

Explicitly routes the agent to exza_get_commander_search_results for paging and to search_stop for discarding the session, which defines the full lifecycle. It does not contrast against exza_search_home_files or exza_list_workspace_files, so an agent must still infer which search family applies.

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

All EXZA Remote 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?