generate_adr_todo

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

The description explicitly claims 'Re-runs are idempotent' while annotations declare idempotentHint: false, a direct contradiction that gives an agent conflicting signals about whether repeated invocations are safe and stable. The description does add useful context beyond the annotations (bounded HTML-comment preservation of manual edits, routing of deleted/superseded ADR tasks to a Stale Tasks section), but the rubric mandates a score of 1 when the description contradicts annotations. Annotation Contradiction is flagged.

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?

Three dense sentences, front-loaded with the core purpose and deliverable. Every clause earns its place: decomposition behavior, milestone linking, manual-edit boundary, idempotency, and stale-task routing. No filler, redundancy, or irrelevant preamble.

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?

The core behavior is well covered, but for a tool with no output schema the description omits what a call returns—where TODO.md is written, success/confirmation output, or how ADRs are discovered beyond the adrDir parameter. The idempotency contradiction also weakens the completeness of the behavioral contract an agent can rely on.

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 all four parameters (phase, scope, adrDir, linkToMilestones) are already documented with defaults and enums. The description's TDD-pairing language adds mild semantic color to the phase parameter, and the milestone-linking mention restates what linkToMilestones already says, so the description does not materially extend the schema. Baseline 3 applies.

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 states a specific verb and deliverable: generate TODO.md from ADRs, then enumerates concrete behaviors (TDD task pairing, milestone linking, manual-edit preservation, stale-task handling). This clearly distinguishes it from sibling ADR-related tools like generate_adr_from_decision, suggest_adrs, and compare_adr_progress, which operate on different artifacts.

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 detailed behavior (decomposing ADRs into implementation tasks, preserving manual edits, tracking stale tasks) strongly implies the intended scenario: turning ADRs into actionable, maintained work items. However, the description never explicitly states when to use this tool versus related siblings such as compare_adr_progress or get_staleness_report, and names no alternatives or exclusion conditions.

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