run_show_command

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It explicitly states the read-only nature, that the server rejects non-show commands, and provides a detailed privilege escalation note: 'show running-config' on IOS/IOS-XE uses privilege-15, while all other commands and all NX-OS commands use the read-only account. This is valuable beyond the bare 'show' in the name and gives the agent important security and permission context.

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 sentences and front-loads the core purpose in the first sentence. The second sentence adds essential behavioral detail about command restrictions and privilege escalation. Every clause earns its place; there is no repetition or filler, making it an exemplary concise description.

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?

The description covers the tool's security model and command constraints effectively, and because an output schema exists, return value details are not required. However, it does not address how this generic tool relates to the 24 sibling get_* commands, which are likely preferred for their specific purposes. Without guidance on when the generic fallback should be invoked instead of a sibling, the description is not fully complete for an agent's decision-making process.

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 input schema provides no descriptions (0% coverage) for 'device' and 'command', so the description must compensate. It clarifies that 'command' must be a show command but does not explain how to specify the device (e.g., by ID, hostname) or the exact command format (e.g., whether to include the leading 'show' keyword). This leaves the agent with incomplete information for constructing valid input.

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 action: 'Run an arbitrary read-only 'show' command on a device.' This identifies a specific verb (run) and resource (a show command on a device), and the word 'arbitrary' distinguishes it from the many specific get_* sibling tools that target particular commands. It also clarifies the read-only scope, leaving no ambiguity about the tool's function.

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 restrictions on what commands are allowed ('Only 'show' commands are permitted') but gives no explicit guidance on when to use this tool versus the many specific get_* siblings. It does not say, for example, 'Use this for show commands not covered by a specific getter' or mention any exclusions. The usage context is implied but not actionable for an agent deciding between alternatives.

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