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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the output is derived map values ('which cells change and by how much, which need more driving and how') and that no BIN is produced here. It does not discuss caching, rate limits, or result format details, keeping it just short of 5.

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 front-load the domain and the input-to-output relationship; the second sentence handles differentiation and scoping cleanly. The phrasing is heavy with domain jargon and punctuation (alpha-N, ///, 0x-style naming), which slows parsing slightly, but no clause is wasted.

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 carries the burden of describing return content, and it does: the cells that change, the magnitude of change, and which regions need more driving data. Together with the schema it tells an agent everything needed to invoke the tool correctly.

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%, with bin_file, log_file, and use_sample fully described in the schema, so the baseline is 3. The prose reinforces that both a DME image and a drive log are required together ('from the same two files') but adds no syntax or format detail beyond the schema.

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 (VE / alpha-N map correction) scoped to a precise domain (BMW E46 M3 S54 MSS54HP CSL conversion), and describes the inputs (DME image + drive log) that drive it. It also differentiates itself from the sibling propose_rfkorr by naming 'VE (alpha-N) map' and from the external tuner, so an agent can tell what this tool produces.

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?

Explicitly frames the tool's role: 'Values only here; the free MSS54HP CSL CONVERT /// TUNER makes the tuned BIN from the same two files' — telling the agent to call this for advisory map values rather than a finished BIN, and that the same inputs feed the downstream tool. It lacks an explicit 'do not use when...' for the read_* siblings, but the context is clear.

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