feedback

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

With no annotations provided, the description carries the behavioral disclosure burden. It explains the feedback flywheel effect: "useful memories rise, unhelpful ones fade." The salience mechanics are already present in the parameter schema, so the description adds useful context without needing to repeat them. It could go further by stating irreversibility or persistence, but the current disclosure is solid.

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 three sentences with no waste. It front-loads the core purpose, then gives the signal mapping, then explains the flywheel effect and a critical caution. Every sentence earns its place.

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?

Given the 100% schema coverage and the simple parameter set, the description is complete enough for an agent to invoke the tool correctly. It specifies when to call, what signals to use, and an important warning. Return value and error handling are not described, but they are not essential for this feedback action.

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 parameters are already fully documented. The description restates some signal meanings but does not add meaning beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting and the description does not conflict with it.

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 verb and object: "Record a quality signal for a recalled memory." It also enumerates the specific signal values, making the tool's purpose unambiguous. It does not explicitly distinguish this from sibling feedback-related tools such as record_outcome or correct, so it misses the top score for sibling differentiation.

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 gives explicit timing guidance: "Call this AFTER using a recall result" and an explicit exclusion: "Do not call this for memories you have not actually used." It does not mention alternative tools or when another tool would be preferable, which prevents a 5.

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