Skip to main content
Glama

Search command outputs

search_output
Read-onlyIdempotent

Search recorded terminal commands and outputs to find exactly which command printed a certain message. Returns matching results with context and metadata.

Instructions

Full-text search over recorded terminal commands, their outputs, and user notes — finds e.g. every command that ever printed 'connection refused'. Returns plain text, one block per match: id, time, cwd, exit code, the command line, and a snippet around the match (secrets are masked by default). Use this to FIND which command said something; use list_commands to browse recent history without a search term, and get_output to read a full output once you have an id. No matches returns an empty result, not an error. Read-only: never re-runs anything.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoonly commands run in this directory or beneath it (absolute path, or '.' for the server's cwd)
exitNoonly this exit code (a number), or 'fail' for any nonzero
hostNoonly commands from this synced machine ('local' = this machine)
limitNomax results (default 20, max 100)
queryYestext to search for in command lines, outputs and notes (substring match; case-insensitive)
sinceNoonly commands newer than this: 30m, 2h, 3d, 1w, or 2006-01-02[ 15:04]
untilNoonly commands older than this (exclusive; same forms as since). Combine with since to bound a time window, e.g. one day.
context_linesNoinstead of a short snippet, show every matching output line with this many lines of context before and after (grep -C style, with line numbers; 0 = matching lines only, max 10). Often avoids a follow-up get_output call.
Behavior5/5

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

Description reinforces annotations by stating read-only and never re-runs commands. Adds that secrets are masked by default, and details the return format including fields and snippet behavior. No contradictions.

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?

Packs essential information into a few sentences with clear front-loading of purpose. No unnecessary words, structured logically from what to when to how.

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?

Given 8 parameters, no output schema, and moderate complexity, the description covers purpose, usage, alternatives, return format, error behavior, and safety. Sufficient for an agent to use correctly.

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 coverage is 100%, so the baseline is 3. The description does not add significant detail beyond what the schema already provides for individual parameters, though it explains the overall search result behavior.

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 clearly states it performs full-text search over terminal commands, outputs, and notes, with a concrete example. It distinguishes itself from sibling tools by specifying when to use list_commands and get_output instead.

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?

Explicitly advises using this tool to find which command produced specific output, and contrasts with list_commands for browsing and get_output for reading full output. Also notes empty returns are not errors.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/soren-achebe/backscroll'

If you have feedback or need assistance with the MCP directory API, please join our Discord server