Sa Scpi

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

No annotations, so the description carries the full burden. It usefully discloses the query convention and the exact set of supported commands (a real capability boundary), but says nothing about error behavior on unsupported commands, whether sa_connect must precede it, or how blocking commands (SWE:WAIT?, *OPC?) behave.

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 core rule is correctly front-loaded in the first sentence, and the command list is arguably necessary information. However, it is dumped as an unbroken run-on wall of mnemonics with no grouping or line structure, making it hard to scan.

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?

An output schema exists, so return values need no explanation, and the command surface is well covered. What is missing for a low-level bridge tool in a large tool family is prerequisite state (connection, mode) and any indication of what to do when a command fails or is unsupported.

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 only 50%, and the description compensates substantially: it enumerates the valid command strings and gives a concrete example format ('FREQ:CENT 915MHz' / 'BAND?'), which is far richer than the schema's one example. The remaining gap is timeout_s, whose units and semantics are left entirely to the name and its default of 60.

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 first sentence gives a specific verb and resource – send a raw SCPI command to the bridge – and the parenthetical clarifies the query convention ('queries end with ?'). It is clear what the tool does, but it never contrasts itself with the many higher-level siblings (sa_get, sa_set, sa_configure, sa_marker), so an agent cannot easily tell when this escape hatch beats them.

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?

There is no explicit when-to-use, when-not, or alternative routing. Given ~30 sibling tools that partly overlap (sa_get/sa_set/sa_trace/etc.), a raw-command escape hatch is exactly the tool that needs 'use this only when no high-level tool covers the operation' guidance, and none is given.

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