log_retrieval_feedback

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

With no annotations, the description carries the full burden. It reveals that omitted fields remain unchanged and cannot be reset to null, and that the tool is conditional on backend configuration. This is good, though could mention error scenarios if query_id is invalid.

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?

Two sentences: first succinctly states purpose and parameters, second adds a crucial condition. No fluff, every sentence adds value.

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?

Covers core behavior and conditions well, given no output schema or annotations. Could mention expected return (likely success/failure) or that query_id must exist, but this is reasonable for a simple feedback tool.

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%, and the description does not add new info beyond what's already in the schema parameters. The baseline of 3 is appropriate since the schema already defines the meaning.

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?

Clearly states its purpose: scoring or annotating a prior kb_search result using its query_id. Distinguishes from sibling tools like get_retrieval_telemetry, which read telemetry, making it unique as a feedback-writer.

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?

Explicitly ties usage to a prior kb_search result via query_id and discloses a critical condition: no effect unless LORE_HARD_NEGATIVE_MINING=true. However, does not explicitly state when not to use (e.g., if backend not configured) or contrast with other feedback mechanisms.

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