scpi_write

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

Far exceeds what the annotations convey (destructiveHint=true, readOnlyHint=false). It discloses side effects ('may change RF, erase data, reset or calibrate'), the safety posture ('No automatic RF mute, preset, error drain or retry is added'), and the meaning of success ('confirms transport completion only') plus the required follow-up (query and read_errors).

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 purpose and identity, then layers constraints and cautions with no filler. Every clause adds a distinct, actionable rule.

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?

For a raw-command escape hatch with one param and no output schema, everything an agent needs is present: scope, safety behavior, syntax limits, and the required post-execution verification step.

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?

With 0% schema description coverage, the description carries full burden and compensates thoroughly: it constrains the command to a non-query, under 128 printable ASCII bytes, and forbids semicolon batches, newlines, AR488++ commands, and binary blocks.

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 ('send ONE ASCII non-query') and explicitly frames itself as an 'expert escape hatch.' The distinction from the sibling scpi_query is inherent: this is for non-queries, queries go elsewhere.

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 when-to-use ('only within the user's requested work after checking the manual') and a clear alternative preference ('Prefer typed tools for supported procedures'), directing the agent to the typed siblings when they cover the procedure.

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