suggest_next_chord

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavioral context beyond those: 'Entirely offline', 'reasons about numerals as symbols and never touches a score or Dorico', and 'common-practice function... what usually follows rather than what must.' This tells the agent the tool is heuristic, symbolic, and side-effect-free in operational terms, not just via hints.

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 well-structured with a lead sentence, a Returns block, and a Note block. It is efficient and front-loaded. Minor redundancy exists: 'read-only' and 'Nothing is written anywhere' both restate what annotations already convey, but this is not harmful given the safety-critical nature of read-only assurances.

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 an output schema present, the description need not detail return fields, yet it still summarizes the return shape. It covers operational context (offline, non-Dorico), limitations (common-practice heuristics), and integration with relevant siblings. For a two-parameter tool, this is comprehensive and leaves no critical gap.

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 schema already documents both key and progression with examples and case conventions. The description adds no extra parameter-level semantics beyond restating that it takes numerals rather than notes. Baseline 3 is appropriate since the schema carries the full burden.

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 specific verb and resource: 'Suggest functional continuations for a Roman numeral progression.' This clearly distinguishes it from sibling tools like analyze_harmony (which extracts numerals) and write_score (which materializes music). The purpose is unambiguous and not a tautology.

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 workflow guidance: 'This takes numerals, not notes. To get numerals out of actual music, run analyze_harmony first and feed its reading in here.' It also names write_score as the way to hear a candidate. These are concrete when-to-use and how-to-chain instructions with sibling tools.

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