use_toolRun any tool from the catalog not exposed in tools/list by passing its name and arguments, at the same pricing as a direct call. Use it to reach unlisted tools on demand.
Free. Run any tool not in tools/list (see tool_catalog). Same pricing as a direct call.
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | Args per that tool's inputSchema. | |
| name | Yes | Tool name (see tool_catalog). |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint false and destructiveHint false, so the key safety posture is structured. The description adds useful context that the tool is free and priced like a direct call, plus the catalog-routing role, but it does not disclose how forwarded tools' side effects are bounded, error behavior, or argument forwarding semantics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences with no filler and a front-loaded pricing note. Every clause contributes routing or cost context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a meta-tool with nested args and no output schema, the description provides the essential routing information and references tool_catalog and the target schema. It remains thin on what the call returns, how failures are surfaced, and whether the wrapper alters the invoked tool's behavior, leaving meaningful gaps for a dispatcher.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already documented in the input schema. The description only points to tool_catalog and the target tool's inputSchema, adding little semantic detail beyond what structured fields provide.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear verb-resource pair ('Run any tool') and scopes execution to tools not exposed in tools/list, while pointing to the sibling tool_catalog for discovery. It is specific enough to separate the dispatcher from the catalog, though the phrase 'any tool not in tools/list' is somewhat circuitous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives an implied usage condition: use this for tools that are not in tools/list and consult tool_catalog. However, it does not explicitly state when not to use it, what happens for tools already in tools/list, or what the alternative direct call conditions are beyond pricing parity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.