decision_write

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

Annotations only declare destructiveHint=false and openWorldHint=false. The description adds critical behavioral context: decisions are irreversible, append-only, and cannot be modified or deleted, which goes well beyond the annotation signals.

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 starts with a clear purpose, then explains semantics, and ends with an Args section. While informative, there is some redundancy between the prose and the Args list that could be tightened slightly.

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 5 parameters, an output schema present, and good annotations, the description covers all necessary context: purpose, parameters, usage constraints, and behavioral traits. No gaps remain.

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% and baseline is 3, but the description adds value by providing examples for each parameter (e.g., 'E.g. "Use SQLite over Postgres."') and explaining defaults and purpose, elevating it above baseline.

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 clearly states the tool records irrevocable decisions with rationale, and explicitly distinguishes it from memory_write by contrasting 'what is true' vs 'what was chosen and why'. It also lists specific use cases (architecture picks, scope cuts, approach selections).

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 explains that decisions are append-only, cannot be updated or deleted, and should be used for choices that future agents should not re-litigate. It also contrasts with memory_write when to use decisions vs memory, providing explicit alternatives.

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