run_tcl

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

With no annotations, the description carries the full burden and does so well: it lists the disabled commands (exec, exit, socket, source, cd, load), the file-write sandbox tied to the session directory, state persistence and how it surfaces via get_conditions, output truncation behavior, and timeout semantics. This is exactly the safety and side-effect context a raw eval tool needs.

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?

Front-loads the core action, then uses a tight bulleted rule list where each entry carries distinct information (syntax, sandboxing, state, return value, truncation, timeout). Dense but no sentence is filler; slightly long for the payoff.

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?

Covers sandboxing, disabled commands, state side-effects, output limits and timeout for a high-power arbitrary-execution tool. An output schema exists, yet the description still usefully clarifies that the Tcl return value is returned and that puts is unnecessary, so nothing an agent needs is missing.

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, and it does: it documents OpenSTA syntax expectations, the brace-wrapping rule for bus bit names with a concrete example, and clarifies timeout_s (0 = no limit) and the default. It adds real meaning beyond the bare 'command' string, though not exhaustively.

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?

States a specific verb and resource ('Run any OpenSTA Tcl command(s) in the live session'), immediately distinguishing it from siblings like find_commands (discovery) and get_status (read-only introspection). An agent can tell what this tool does without opening the schema.

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?

Gives explicit conditional routing: use find_commands when unsure of a command name and `help <command>` when unsure of options, and covers the timeout semantics. It does not, however, tell the agent when to prefer the dedicated siblings (report_timing, report_power, get_summary) over hand-written Tcl, which is the main routing decision for this tool.

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