art.memory.add_reference

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

With no annotations present, the description carries full responsibility. It states 'add' (a mutation) but does not disclose idempotency, whether it validates asset existence, whether it overwrites duplicates, or what it returns. No mention of side effects or prerequisites. A bare one-liner, so 2.

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?

One short sentence, no fluff. It is front-loaded with the action and object. However, it lacks any structural breakdown (e.g., when/how to use), so while concise it is not information-dense. Average 3.

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?

Missing essential context: what a 'reference' is, how it differs from anchors/decisions, whether multiple references per asset are allowed, and what 'approved' means relative to the status field. The terse description leaves an agent guessing about semantics and preconditions.

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?

Every schema property has an explicit description (e.g., 'Asset ID this reference points to', 'Reference strength'), giving high schema coverage. The description itself adds no extra meaning beyond the word 'approved', which conflicts slightly with the status field. Baseline 3 because the schema does the heavy lifting.

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 verb 'add' and object 'reference' clearly indicate a write operation, and the domain 'art memory' situates it among memory management tools. The word 'approved' adds intent but slightly conflates the operation with a status filter; however, it distinguishes from add_anchor/add_rejection siblings. Minor ambiguity, so 4.

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 guidance on when to use this vs. art.memory.add_anchor, add_rejection, or resolve_references. Missing criteria such as 'when you need to store a new reference' or 'prefer add_reference for...'. Only implicit context from the name. Score 2.

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