Skip to main content
Glama

mcphost

by dev.mcphost

host.tool_run

Debug run of a published tool: the same sandbox and limits as a real call, but returns full stdout and stderr (each capped at 64 KiB) and the exit code alongside the result, and records no calls row and no metering. Only kinds with a notion of a subprocess (python) support this; other kinds return tool_run_unsupported. Rate-limited to 30 calls per tenant per minute, independent of host.usage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argsYes
nameYes
tenant_keyNoThe key `signup` returned. Required only when this connection carries no Authorization: Bearer header -- when both are present, the header wins.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly: it discloses sandbox equality, 64 KiB caps on stdout/stderr, exit code inclusion, absence of calls/metering, unsupported-kinds error, and rate limiting independent of host.usage. This is exemplary behavioral transparency for a debug tool.

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 dense, front-loaded sentences with no filler. The core purpose appears first, followed by behavior, constraints, and rate limiting. Every sentence adds information relevant to calling the tool correctly.

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?

Despite no output schema and no annotations, the description covers the essential context: behavior, output limits, side effects (no metering), supported kinds, error case, and rate limit. Given the tool's complexity, this is a complete and self-sufficient description for an agent to decide when and how to invoke it.

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

Parameters2/5

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

Schema description coverage is only 33% (only tenant_key is described), and the description does not explain the 'name' or 'args' parameters. It references 'published tool' and 'kinds', which indirectly hints at name, but the meaning of 'args' and how name relates to published tools is left to inference. With low coverage, the description needed to compensate and did not.

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 states a specific verb and resource: 'Debug run of a published tool', and clearly contrasts it with 'a real call', distinguishing it from sibling tools like host.tool_call and host.tool_test. It also specifies the unique output characteristics (stdout/stderr, exit code) that make this a distinct debugging operation.

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?

The description clearly implies use for debugging by contrasting with a 'real call' and explaining when it records no metering and no calls row. It also states the limitation to subprocess-supporting kinds and the rate limit, giving concrete conditions. However, it does not explicitly name alternative tools or state 'use X instead when you need metering', so a small gap remains.

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

All mcphost toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools target a clearly distinct resource or lifecycle stage, with billing, secret, and tool-publishing groups nicely separated. The main ambiguity is among host.tool_call, host.tool_test, and host.tool_run, which all invoke a published tool in slightly different modes; the descriptions clarify this, but the names alone could mislead an agent.

Naming Consistency4/5

The namespace prefixes billing.* and host.* provide a consistent organizational pattern, and host.tool_* tools use a predictable resource-action style. Deviations like signup, host.quickstart, host.usage, and host.whoami break the pattern, but they are few and still readable.

Tool Count4/5

At 17 tools, the server is slightly over the typical well-scoped 3-15 range, but the breadth is justified by the multi-tenant hosting domain: signup, billing, tool lifecycle, secrets, debugging, and usage observability each need dedicated tools. Every tool has a plausible role, so the count feels reasonable rather than bloated.

Completeness3/5

The tool lifecycle is well covered with publish, list, test, run, call, logs, and remove, and billing/usage/signup are present. Notable gaps remain, though: secret_set has no corresponding secret_delete, there is no tenant update/delete operation, and host.registry_publish references admin.tenant_verify_namespace, which is not exposed in this tool set.

Resources