record_decisionStore architectural and design decisions in your project database. Capture titles, reasons, and impact to keep a clear decision history for your codebase.
Records an architectural or design decision to the database.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| reason | No | ||
| status | No | active | |
| repo_path | No | ||
| description | No | ||
| consequences | No | ||
| affected_files | No | ||
| affected_modules | No | ||
| affected_features | No |
Changes observed during successful MCP inspections.
v0.9.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose the key traits (write operation, not read-only, idempotent, non-destructive, closed-world). The description adds only "to the database," which restates persistence without explaining dedup behavior on idempotent writes, whether an existing decision is overwritten, or whether repo_path scopes the record. Little value beyond the annotations.
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?
A single compact sentence with no filler and the action front-loaded. It is efficient, though the brevity is under-specification rather than disciplined conciseness.
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 nine-parameter mutation tool with no output schema and zero schema description coverage, one sentence is far from sufficient. An agent cannot tell which fields are required, what values status accepts, or how the affected_* fields relate to repo_path.
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?
Nine parameters with 0% schema description coverage, and the description names none of them — not the required title, nor status, reason, consequences, repo_path, or the three affected_* arrays. With this coverage gap the description must compensate and it does not at all.
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?
States a clear verb+resource ("Records an architectural or design decision") with a domain qualifier that loosely separates it from sibling record-tools. However, it gives no signal for distinguishing a "decision" from record_rule, record_task_lesson, or record_procedure_outcome, so the agent must guess. Adequate but shallow.
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?
No when-to-use guidance, no prerequisites, and no mention of the closely related sibling tools (record_rule, record_task_lesson, record_task_observation) that also write structured records. The agent is left to infer whether a given piece of knowledge is a decision, rule, or lesson.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.