refresh_hard_negatives

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

With no annotations, the description carries full burden. It discloses that the tool writes to knowledge.hard_negative_pairs and requires LORE_HARD_NEGATIVE_MINING=true. However, it does not mention if the operation is idempotent, potential side effects (e.g., does it delete existing pairs?), or error behaviors. The core behavior is clear but lacks depth.

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?

Three sentences, no wasted words. First sentence defines purpose, second adds usage context, third states a prerequisite. Efficient and well-structured, fitting more information into a compact form.

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 simple parameters and existing output schema, the description covers core functionality, parameters, and a prerequisite. It lacks explicit guidance on the format for the 'since' parameter or error conditions. However, the output schema likely covers return values, so completeness is adequate.

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 0%, so the description must compensate. It explains both parameters: 'since' is for incremental refresh and 'dry_run' returns counts without writing. This adds needed meaning beyond the schema's raw structure. The explanation is sufficient but could specify the expected format for 'since' (e.g., ISO timestamp).

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?

Description clearly states the tool scans retrieval telemetry and upserts hard negative pairs into a specific table. The verb 'scan' and 'upsert' precisely describe the action, and the resource 'knowledge.hard_negative_pairs' is explicit. This distinguishes it from siblings like get_hard_negatives (which retrieves) and get_retrieval_telemetry (which only scans).

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 clear usage hints: 'Use since= for incremental refresh' and 'dry_run=true returns counts without writing.' It also notes a required environment variable. However, it does not explicitly state when not to use this tool compared to alternatives, missing a chance to guide selection among siblings.

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