gx3_run_command

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

Without annotations, the description carries the disclosure burden. It clearly discloses that the tool rejects mutating commands and demo generation, and that local artifacts are confined to GX3_MCP_OUTPUT_DIR. It does not detail side effects like exit-code handling or logging, but the safe-by-construction framing is transparent enough for an escape-hatch tool.

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?

Four terse sentences, front-loaded with the purpose and immediately followed by restrictions and routing guidance. Every sentence earns its place: purpose, safety guardrails, artifact confinement, and sibling preference.

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 output schema and no annotations, the description covers the key operational constraints an agent needs: allowed command types, forbidden commands, artifact confinement, and preference over siblings. It does not explain what output the command returns or how the agent should parse it, but for a generic escape hatch wrapping a CLI, the presented constraints are more important than return details.

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 50%: 'command' and 'root' are described in the schema, while 'args' and 'timeout_seconds' are only structurally defined. The description reinforces that 'command' must be MCP-allowed and read-only, which adds selection semantics beyond the schema. It does not explain how 'args' maps to CLI arguments, but the name plus the overall escape-hatch concept is reasonably self-evident.

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 identifies a specific action ('run any MCP-allowed, project-read-only GX3 CLI command') and clearly distinguishes it from typed sibling tools by calling itself an 'escape hatch.' It names the resource (GX3 CLI commands) and the constraints, which effectively separates it from the more specialized siblings.

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?

Explicitly states when to use the tool ('when no typed tool fits' is implied by 'escape hatch' plus 'Prefer the typed tools above when one fits'), and also states exclusions: project-mutating commands and local demo generation commands are rejected. This gives clear routing guidance and prevents misuse.

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