memory_feedback

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

The description discloses important behavioral traits beyond the annotations: it explains the learning-signal mechanism ('positive feedback raises a memory's ranking... negative feedback lets it fade'), specifies scope ('across all of the user's tools'), and highlights the silent failure for shared domains. This adds significant context that the raw annotations (destructiveHint, openWorldHint) do not convey, and it does not contradict any annotation.

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 concise (three sentences) and well-structured: it opens with the core purpose, then explains the mechanism and timing, and finishes with an important caveat. Every sentence carries essential information with no filler or redundancy.

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 tool's moderate complexity, the description covers all critical aspects: what it does, when to call it, the effect on memory ranking, the scope, and a failure mode. No output schema is present, so not describing return values is acceptable. The description is complete for an agent to invoke the tool correctly.

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 input schema already fully describes both parameters with clear meanings and ranges (outcome from -1 to 1, atom_ids as array of strings). The description adds value by clarifying that atom_ids come from 'memory_read results' and by connecting the outcome values to the ranking effect ('positive feedback raises... negative feedback lets it fade'). While this is modest, it enhances the schema's information for a high-coverage case.

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's purpose: 'Report whether memories returned by memory_read were actually helpful.' It uses a specific verb ('report'), a specific resource ('memories'), and a clear context ('returned by memory_read'). This distinguishes it from sibling tools like memory_write (writing), memory_read (reading), and memory_delete (deleting).

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 provides explicit guidance on when to use the tool: 'Call it right after you act on (or reject) recalled memories.' It also clarifies what the tool is not ('not a log') and includes a caveat about when it won't work ('rating a memory that lives in a shared room silently does nothing'), effectively serving as a when-not-to-use warning. This is strong usage guidance.

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