set_cursors

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

With no annotations, the description carries the full burden and does substantial work: state retention ('omitted mode is retained'), hardware restriction ('DHO-only'), a prerequisite ('requires XY timebase'), and rejection behavior ('rejects positions here'). It stops short of disclosing error outcomes, whether settings persist across sessions, or side effects on existing measurements, so it's strong but not exhaustive.

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?

Extremely dense with zero filler: the first clause names the operation and return, and each subsequent clause adds one distinct constraint or routing rule. Front-loads the core purpose before diving into mode-specific details.

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 10-parameter, 4-mode tool with no annotations and no output schema, the description covers the hard parts: mode validations, DHO-only quirks, and alternative routing to scpi_execute. Gaps remain on the return readout format (no output schema to back it up) and cursor_type's interaction with modes, but those are minor against the breadth covered.

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 already covers 70% of parameters with descriptive text; the description adds the crucial mode→parameter mapping (which params are valid in which mode) and the OFF/XY constraints, directly compensating for the three undocumented enums (mode, track_axis, cursor_type). The value added is meaningful but not exhaustive – cursor_type semantics are only implicitly covered by 'type for MANUAL'.

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 ('Set cursors') plus output behavior ('return readouts'), and differentiates itself from sibling scpi_execute by explicitly reserving XY positioning for that tool on DHO814. An agent can distinguish this from get_cursor_values (read) and scpi_execute (generic command execution) 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?

Provides explicit mode-to-parameter routing: MANUAL uses source/type, TRACK uses source_a/source_b/track_axis, OFF accepts no positions or sources, and XY requires an XY timebase and belongs on scpi_execute instead. This is exactly the when-and-when-not guidance a selector needs, including a named alternative.

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