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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds the non-obvious behavior that the baseline run is auto-selected by matching endpoint, OCPI version and module rather than being supplied by the caller. It also discloses the three-part shape of the comparison. It does not say what happens when no comparable prior run exists, which is a meaningful edge case for a delta tool.

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?

One front-loaded sentence carries the scope, the baseline-selection rule, and the output categories, followed by a short framing question. No filler and nothing restated from the title or schema.

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 one required parameter, no output schema and a read-only annotation, this is nearly complete: the comparison basis and result categories are stated. The remaining gap is behavior when no comparable prior run is found, which an agent would need in order to interpret an empty or failing result.

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 100% and the schema already explains where reportId comes from (list_runs or a start tool). The description adds real meaning beyond that: the single id implicitly determines both sides of the comparison, so the agent understands it is not passing two run ids.

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 description names a specific verb (compare) and precisely delimits the resources: this run versus the previous comparable run against the same endpoint, OCPI version and module. It also enumerates the result categories (newly failing, recovered, no longer graded), which distinguishes it from siblings like chargerdojo_get_run_checks or chargerdojo_get_run_verdict that report state rather than deltas.

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?

Usage context is stated plainly with the framing question 'what changed since my last run', which tells an agent the situation that selects this tool. It does not name alternatives or exclusions (e.g., use get_run_checks for a full per-check listing, or compare_ocpi_versions for cross-version diffs), so routing is implied rather than explicit.

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