decision_write

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

The description clearly discloses that decisions are append-only, cannot be updated or deleted, and are irreversible. This adds important behavioral context beyond the annotations, which only declare destructiveHint false and openWorldHint false. An agent knows this is a permanent, high-commitment write.

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 front-loaded with the core purpose, then provides a concise differentiation from memory, followed by a compact args list. Every sentence contributes to correct usage; there is no redundancy or filler.

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 write tool with an output schema, all parameters are documented, the append-only semantics are explicit, and the tool's role among siblings is clarified. Nothing needed for a correct call is missing.

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 every parameter. The description largely restates these definitions, but it adds a helpful example for 'decision' ('Use SQLite over Postgres') and clarifies the intent of 'alternatives' as rejected options. This is adequate but not additive beyond the schema.

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-resource pair ('Record an irreversible decision') and immediately clarifies the tool's scope. It also distinguishes decisions from memory writes ('Memory captures what is true; decisions capture what was chosen and why'), which separates it from the memory_* sibling tools.

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?

It states exactly when to use decisions ('choices that future agents should not re-litigate') and gives concrete examples like architecture picks and scope cuts. It also contrasts decisions with memory, but it does not explicitly mention the read-side sibling tools (decision_list/decision_get) or state when not to use it.

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