art.memory.add_decision

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

Annotations are absent, so the description must carry the burden for behavioral disclosure. While it states the action ('Add a new decision record'), it does not disclose side effects, such as whether the decision is immutable, whether it verifies referenced decisions/relationships, or what the response format is. For a write operation with potential consequences (relationships, provenance), this is a notable gap. The description adds no behavioral insight beyond the action itself.

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 a single short sentence with no structure. It is under-specified: for a tool with 10 parameters, it offers no structured overview of parameters or their relationships. It is minimal but not adequately concise in the sense of covering key points—it's just terse without being informative.

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 tool has 10 parameters (6 required) and no annotations. The description plus schema collectively make it usable: the schema defines required fields and constraints. However, missing context like error conditions, mutability, duplicates (e.g., what happens if the same ID already exists), or integration with related tools limits completeness. It's adequate for basic invocation but lacks deeper contextual safeguards.

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 schema provides detailed descriptions for each field, so the description itself adds very little. The description mentions 'art decision record' but does not map to specific parameters or explain the required 'style' object vs. optional fields. The goal 'such as' style may make sense intuitively, but an agent would rely on the schema likely enough; the description contributes no high-level semantic guidance or parameter rationale.

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 ('Add a new art decision record'), which identifies what the tool does. However, it does not distinguish this from sibling tools like art.memory.add_reference or art.memory.add_rejection, leaving some ambiguity about the specific scope. The term 'art' and 'decision' are clear enough, but the lack of differentiation from similar memory-add tools lowers the score.

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?

There is no guidance on when to use this tool versus alternatives. The description provides no context about prerequisites (e.g., must reference an existing style), no mention of when not to use it, and no comparison to siblings like find_decisions or add_anchor. This leaves the agent to infer usage entirely from the tool name and schema.

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