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

The description explicitly states the operation is read-only: 'WITHOUT rewriting its rates' and calls it 'the read sim_calibrate.' However, annotations declare readOnlyHint=false and destructiveHint=true, directly contradicting the described behavior. The description does add useful behavioral detail (per-trace diagnostics, one-case-at-a-time replay, lossy-encoding caveats), but the annotation contradiction is disqualifying under the rubric.

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?

The description is dense but every clause earns its place: purpose, alternative, metrics, diagnostics, log format, replay model, and a caveat are all included. It is somewhat run-on with multiple parentheticals, but it is front-loaded with the core purpose and read-only distinction, so it remains efficient for its complexity.

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?

Given there is no output schema, the description does well to name the returned metrics and per-trace diagnostics that name activities that could not fire. It also explains the required log format and the modeling assumption (per-case workflow). It could go further by enumerating the specific lossy-encoding caveats, but overall it provides enough context for correct invocation.

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 100% schema coverage, the baseline is 3, and the description adds genuine value beyond the schema for the log parameter: it specifies exact CSV columns (case_id, activity, timestamp), the sim_dataset shape, and that activities are transition ids. The id parameter is simple and adequately covered by the schema as 'model id.'

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 and resource: 'Check how well a stored model matches an observed event log' and immediately distinguishes itself from sim_calibrate by framing it as the read-only conformance component. It further lists concrete conformance metrics (fitness, precision, generalization, simplicity), so an agent can tell exactly what the tool evaluates.

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 description explicitly positions this as 'the read sim_calibrate bundles into calibration, offered on its own,' giving a clear when-to-use signal versus the calibration sibling. It also gives concrete exclusion guidance: the log is replayed per-case from the initial marking, so a resource net with shared places 'will not fit.' An agent gets actionable selection criteria.

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