execute

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that privileged commands require human approval, that commands run on the target host, and that pipelines are supported. It also notes the need to call start_server first. This is substantive behavioral context, though it omits details like timeout behavior or return values, which are not covered elsewhere.

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 three sentences, front-loaded with the core purpose, and includes a concrete example for the pipeline. It avoids fluff and keeps the essential information (approval, target host, dependencies) in a compact form. A slightly tighter phrasing could improve it, but it is well-structured.

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 tool with 8 parameters, nested objects, and no output schema, the description covers the key operational details: execution, approval, host selection, and pipeline support. The schema handles parameter definitions, so the description does not need to repeat them. It lacks mention of edge cases like timeouts or error handling, but given the schema richness, it is reasonably complete.

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?

The schema coverage is 100%, so each parameter already has a description. The tool description adds value by explicitly contrasting `pipeline` vs `argv` for single vs multi-stage commands, which complements the schema. This goes beyond the baseline and directly aids parameter selection.

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 the tool's purpose: execute a command through sudo-proxy with human approval. It specifies the target host (local by default) and mentions a prerequisite dependency on start_server, which helps differentiate it from siblings. However, it does not explicitly contrast with update_host, so it's not a perfect 5.

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?

The description provides a direct usage prerequisite: 'Call start_server first if sudo-proxy is not already running.' It also implicitly distinguishes between pipeline and argv usage, but it does not give explicit when-not-to-use guidance for either sibling. The dependency on start_server is clear, which is strong for this dimension.

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