Skip to main content
Glama

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Run a command in your shell

bash

Runs a bash command in this account's jailed, read-only shell, which holds live data programs as well as files. Public records: funding (SEC Form D raises, funding recent for this month's), company-hiring (open roles from company job boards), h1b-hiring, ucc, fcc, fda, us-trademarks, us-business-license, us-motor-carriers, sec-filings, webcertificates. People and companies: outreach (who holds a role, work emails checked against the mail server), social, dns, rank, trade (importers and shipments), pplx. Plus realestate-us, places, model-prices, ocr, xlsx, pdftext, browser.

help lists what is on; programs list shows every program and what it bills; programs enable SLUG turns one on. <program> --help gives its usage. Metered programs draw on the account's prepaid credits (see the credits tool).

Also the account's connected drives (/dropbox, /googledrive …) and /catalog to search them. Nothing can be written except /tmp, which is this session's own scratch.

ONE SHELL PER SESSION. Its cwd and /tmp persist across calls, and it is the same shell checkout_workbook writes a workbook into — so check a workbook out, edit it here, and commit_workbook it, with no session id to pass between them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesA bash command line. Pipelines, globs and control flow work; a redirect anywhere but /tmp is refused.
contextNoExplain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
llm_modelNoThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only give openWorld/idempotent/readOnly/destructive hints; the description adds substantial extra behavior: writes are confined to /tmp, redirects elsewhere are refused, one persistent shell per session sharing cwd and /tmp across calls, and metered programs spending prepaid credits. This is exactly the kind of operational context an agent needs to call it safely.

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?

Front-loaded with the core behavior and persistence/billing rules, but the two long program catalogues are dense and could be trimmed since `help` and `programs list` are described as the discovery path. Overall the sentences earn their place and structure is clear.

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 no-output-schema tool that executes arbitrary commands, the description covers the environment, persistence semantics, write restrictions, billing model, and its handoff to the workbook tools. Nothing critical to correct invocation appears missing.

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 parameter contracts are already documented, but the description meaningfully enriches the `command` parameter by cataloguing the available programs and the enable/billing mechanics that shape what a valid command looks like. It does not, however, add formatting or syntax guidance beyond the schema's 'pipelines, globs and control flow' note.

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 ('Runs a bash command in this account's jailed, read-only shell') and immediately characterizes the environment and the data programs reachable from it. An agent can distinguish this from the workbook-manipulation siblings 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?

Gives clear operating context (what's available, how to discover it via `help`, `programs list`, `programs enable`, `<program> --help`) and an explicit routing rule tying it to a sibling flow: check a workbook out, edit it here via bash, then commit_workbook. It stops short of stating when-not-to-use bash in favor of a dedicated sibling tool.

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

All hedwigai toolsInspect
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