get_hard_negatives

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

No annotations are provided, so the description must carry the full burden. It discloses that the tool is a read operation, specifies the source table, and mentions sorting. However, it does not address safety, permissions, idempotency, or potential side effects.

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, using two short sentences to convey the tool's action, filters, and sorting. No redundant information is present.

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?

The description covers the main functionality and filters but does not mention the default limit (100) or pagination behavior. Since an output schema exists, return values are not needed, but the lack of limit clarification is a minor gap.

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 adds needed meaning. It explains that signal_type accepts values like 'explicit/behavioral/all', and that doc_id and query_text_like are filter names. However, it omits description of the 'limit' parameter and does not fully detail all parameter formats.

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 action (read), the resource (hard negative pairs from knowledge.hard_negative_pairs), and the key filters (signal_type, doc_id, query_text_like). It also mentions sorting, making the tool's purpose unambiguous and distinct from sibling tools like refresh_hard_negatives.

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 does not provide any guidance on when to use this tool versus alternatives, such as when to use refresh_hard_negatives instead. No explicit when-to-use or when-not-to-use information is given.

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