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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false, closed world), and the description usefully adds that the tool is experimental, returns values only, and does not produce a file — a real behavioral trait beyond the annotations. It stops short of describing cost, limits, or failure modes on bad BIN/log input.

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?

Two dense sentences that lead with the vehicle/ECU context and the concrete output, then the experimental caveat. Every clause carries information, though the first sentence is packed with parentheticals.

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?

With no output schema, the description must convey returns, and it does: the rf_korr table plus per-cell evidence, values only, no file emitted. Missing only format/units detail for the returned values, which is minor for a preview tool.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: the log must contain exhaust temperature, and the BIN must be the MSS54HP calibration partial. That qualifies the otherwise generic file-object parameters.

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 (propose) and resource (rf_korr table / KF_RF_KORR_DRREL) plus the exact inputs it derives from (DME image and a drive log with exhaust temperature). It is clear on its own, but it does not differentiate itself from the sibling propose_ve, which follows the same propose-from-files pattern.

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?

The 'experimental in the app; values only — the WORKS build of TUNER makes the file' line hints at when this preview-only tool is appropriate, and use_sample implies a no-files-yet path, but no explicit when-to-use/when-not or alternative (e.g. vs propose_ve) is named.

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