Skip to main content
Glama

mcphost

by dev.mcphost
OverviewDiscussionsAdmin

host.tool_publish

Publish a tool of a registered kind (chain, echo, http, python, wasm) under this tenant's namespace. Call host.quickstart(kind) first for a filled-in example spec and the full publish-to-call sequence. Name must match ^[a-z][a-z0-9_]{1,40}$; a rejection names the failing field and a corrected example. Try host.tool_test before a real call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesWhich registered kind to publish under, e.g. echo, http, python.
nameYesLocal name for the new tool; must match ^[a-z][a-z0-9_]{1,40}$.
specYesThe kind-specific spec object; see host.quickstart(kind) for a filled-in example.
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.

  1. Changed3 schema fields changed
    • addedInput schema / properties / kind / description
      Added value: +"Which registered kind to publish under, e.g. echo, http, python."
    • addedInput schema / properties / name / description
      Added value: +"Local name for the new tool; must match ^[a-z][a-z0-9_]{1,40}$."
    • addedInput schema / properties / spec / description
      Added value: +"The kind-specific spec object; see host.quickstart(kind) for a filled-in example."
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral disclosure burden. It discloses the name validation regex and rejection behavior (naming the failing field and a corrected example), which is useful. However, it does not disclose overwrite/idempotency behavior, permission requirements, or side effects beyond the verb 'publish'.

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 sentences accomplish purpose, prerequisites, validation, error behavior, and testing guidance with no filler. The main action is front-loaded, and every clause earns its place.

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?

Given no output schema, the description gives enough to call the tool correctly: supported kinds, prerequisite quickstart, name validation, rejection format, and post-publish testing. It does not describe the success response shape, but the quickstart reference is positioned to fill that gap.

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 baseline is 3, but the description adds value by listing the complete set of supported kinds (chain, echo, http, python, wasm) beyond the schema's 'e.g.' examples. It also directs the agent to host.quickstart(kind) for the spec shape, compensating for the nested spec's lack of detail.

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 action and resource: publish a tool of a registered kind under the tenant's namespace, with supported kinds enumerated. This clearly differentiates it from closely related siblings such as host.registry_publish and host.tool_call.

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 instructs calling host.quickstart(kind) first to obtain a filled-in example spec and the publish-to-call sequence, and recommends host.tool_test before a real call. This gives clear workflow context, though it does not state explicit exclusions or when not to use the tool.

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
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