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

Annotations already declare readOnlyHint and idempotentHint true, and the description reinforces this with 'Pure computation.' It adds substantial behavioral context: validation errors are returned in the result rather than as schema rejections, history loading adds predicted durations and changes analysis mode (planned vs. predicted), and the prediction model's basis (identical/model/none) is disclosed. No contradiction with annotations; the description enriches understanding of side-effect-free behavior and failure modes.

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 well-organized: the core purpose and output summary come first, followed by a clearly delimited 'Analysing against real history' section for the advanced history-based prediction. While longer than typical, every sentence carries informational weight—no filler. The structure supports scanning, though it could be slightly tighter, hence a 4 rather than a 5.

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 tool with 8 parameters, nested objects, and an output schema, the description covers the essential behavior: what is computed, what history does, how prediction works, and that validation findings are included. The output schema handles return structure, so the description does not need to spell it out. All relevant scenarios—timing questions, critical path diagnosis, contention checks—are addressed, and the prediction context is fully described. Nothing essential is missing.

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%, so every parameter has a schema description. The tool description goes beyond that by clarifying the interplay between parameters: how history and program_id+token load runs, how finishAt vs. startAt are prioritized, how useDurations depends on history, and the semantics of predictionContext fields like userTags and verdicts. This adds meaningful context, though it does not individually elaborate on every parameter, so it stops short of a 5.

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 opens with a precise, action-oriented statement: 'Resolve a Rhylthyme program onto the clock and report what the live runner will do,' enumerating specific outputs (step timings, makespan, critical path, binding constraints, conflicts, slack). It further distinguishes itself from siblings like visualize_schedule by explicitly framing itself as the analysis step before visualization, and from validate_program by noting it returns validation findings as part of its computation. This makes the tool's purpose unmistakable and clearly differentiated.

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 gives explicit use cases: answering schedule timing questions, diagnosing why a schedule is longer than expected, checking equipment contention before visualizing. It also references sibling tools (load_run, list_my_programs) for history and clarifies when to use history vs. program_id. However, it does not explicitly contrast with validate_program or preview_timeline, so an agent might not know when to prefer this over those, leaving a slight gap in exclusion guidance.

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