Invoke a tool by name. input is validated against the target schema before dispatch.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Exact tool name to invoke (e.g. "accounting-invoices-create"), as returned by list_tools. | |
| input | No | Arguments object validated before being forwarded to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments. |
Changes observed during successful MCP inspections.
Input schema / properties / input / descriptionPrevious value: -"Arguments object forwarded verbatim to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments."New value: +"Arguments object validated before being forwarded to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments."Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / properties / input / additionalPropertiesAdded value: +{}Input schema / properties / input / descriptionAdded value: +"Arguments object forwarded verbatim to the target tool. Its shape matches that tool's input schema (fetch it with describe_tool_input). Omit for tools that take no arguments."Input schema / properties / input / propertyNamesAdded value: +{
+ "type": "string"
+}Input schema / properties / input / typeAdded value: +"object"Input schema / properties / name / descriptionAdded value: +"Exact tool name to invoke (e.g. \"accounting-invoices-create\"), as returned by list_tools."Input schema / requiredPrevious value: -[
- "name",
- "input"
-]New value: +[
+ "name"
+]Input schema / properties / argumentsRemoved value: -{
- "additionalProperties": {},
- "description": "Arguments for the target tool as a JSON object, matching the schema returned by describe_tool_input.",
- "properties": {},
- "type": "object"
-}Input schema / properties / inputAdded value: +{}Input schema / properties / name / descriptionRemoved value: -"The name of the tool to execute"Input schema / requiredPrevious value: -[
- "name"
-]New value: +[
+ "name",
+ "input"
+]Input schema / properties / argumentsAdded value: +{
+ "additionalProperties": {},
+ "description": "Arguments for the target tool as a JSON object, matching the schema returned by describe_tool_input.",
+ "properties": {},
+ "type": "object"
+}Input schema / properties / inputRemoved value: -{
- "additionalProperties": {},
- "description": "Input parameters for the tool as a JSON object",
- "propertyNames": {
- "type": "string"
- },
- "type": "object"
-}Input schema / properties / nameAdded value: +{
+ "description": "The name of the tool to execute",
+ "type": "string"
+}Input schema / properties / tool_nameRemoved value: -{
- "description": "The name of the tool to execute",
- "type": "string"
-}Input schema / requiredPrevious value: -[
- "tool_name"
-]New value: +[
+ "name"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare openWorldHint=true, idempotentHint=false and readOnlyHint=false, and the description adds a genuinely useful trait: input is validated against the target schema before dispatch. However, it does not warn that this dispatcher can trigger destructive write operations in downstream tools (which sits awkwardly with destructiveHint=false) or how errors are surfaced.
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?
Two short sentences, no filler, with the core action front-loaded and the validation behavior following. Nothing could be trimmed without losing information.
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-dispatch tool with a nested free-form input object and no output schema, the description omits what the caller gets back (raw result vs wrapped envelope) and how downstream failures are reported. The pre-dispatch validation note is helpful but the behavioral picture is incomplete.
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% and both parameters are well documented inline (exact tool name, arguments shape, omit for no-arg tools). The description adds no parameter detail beyond the schema, so the baseline 3 is appropriate.
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?
States a specific verb (Invoke) and resource (a tool by name), and the second sentence clarifies the dispatch semantics. It is clearly distinguishable from list_tools, describe_tool_input and list_scopes, which enumerate rather than execute.
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?
Implicitly the entry point for actually running a tool discovered via list_tools, but the description gives no explicit when-to-use or when-not guidance and does not name the alternative patterns (e.g. that discovery should precede execution). Usage is inferable only from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.