run_show_commands

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

Despite no annotations, the description discloses that commands are executed sequentially and stop on first failure. It also notes a critical behavioral trait for JunOS: dropping pipe stages under json/xml output. This adds significant value beyond the schema.

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 concise with 7 sentences, front-loading the primary purpose and execution behavior. It then lists parameter descriptions. The structure is logical, though could be slightly tighter by using bullet points for parameters.

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?

Given no annotations and 4 parameters, the description covers usage, behavior, and parameters well. It mentions an output schema exists but doesn't explain return values (acceptable since schema is present). However, it lacks details on error handling (e.g., error messages on command failure) and session management.

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 0%, so the description must compensate. It describes each of the four parameters: hostname (must exist in config.ini), commands (list), output_format (with JunOS caveat), config_path (default search behavior). This provides essential context beyond name and type.

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 'Run multiple CLI show commands on the device in a single session.' It distinguishes from the sibling tool run_show_command by specifying that commands execute sequentially and stop on first failure, and offers an alternative approach for ignoring errors.

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 explicitly says when to use this tool (multiple commands in one session) and when not (to run all commands regardless of errors, use run_show_command per command). It provides clear context for execution behavior. However, it does not mention the sibling run_show_command_batch.

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