run_tool

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

With no annotations provided, the description carries the full burden. It only says 'Execute any registered tool' without disclosing side effects, security implications (e.g., running arbitrary bash), error behavior, or return format. This is a significant gap for a tool that can invoke arbitrary functionality.

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 a single, concise sentence that front-loads the main purpose and then lists examples. Every word earns its place; there is no redundancy or fluff.

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 generic tool with no output schema and no annotations, the description is too sparse. It fails to specify expected return values, error handling, or the security context of executing tools like bash. The complexity of a dispatcher warrants more guidance than this.

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 coverage is 100%, with 'name' and 'params' both described. The description adds a list of tool name examples, which gives some context, but it does not elaborate on how 'params' should be structured depending on the chosen tool. This is only a slight improvement over the schema.

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 clearly states that this tool executes any registered tool, with specific examples (bash, read, write, edit, glob, grep, git, web_fetch, web_search, memory_*). This distinguishes it from the many sibling tools that each perform a specific, dedicated action.

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?

Usage guidance is implied rather than explicit. Saying 'Execute any registered tool' suggests it is a generic dispatcher, but the description does not explicitly say when to prefer this over dedicated siblings or mention any exclusions or alternatives.

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