Record decision

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

Discloses behavior beyond annotations: writes a markdown file plus a git commit, nothing is overwritten or removed, the decision appears in every future resume context, and no permission is needed. These details enrich the minimal readOnly/destructive hints without contradicting them.

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 sentences with no filler. The primary action is front-loaded, and each sentence adds meaningful context: what it writes, safety properties, and usage criteria. Highly concise and well structured.

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?

Covers the core aspects an agent needs: action, side effects, when to use, and correction mechanism. Missing some details like output format or error conditions, but with full schema coverage and no output schema, it is sufficiently complete 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?

The input schema fully describes all four parameters (100% coverage), so the baseline is 3. The tool description itself does not add extra parameter meaning beyond what the schema already provides.

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 resource: 'Append a decision the user has settled.' It clearly identifies the tool's function and distinguishes it from the record_* siblings by focusing on decisions, though it does not explicitly contrast with alternatives like record_constraint.

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?

Provides explicit when-to-use guidance: 'Capture autonomously as you observe it — no permission needed — but only for things a future session could not re-derive; skip restatements and progress narration.' This tells an agent when to invoke it and what to avoid, though it does not name alternative tools for other record types.

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