Reconstruct research evidence

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

With no annotations, the description carries the full behavioral burden and does a good job by explicitly stating that missing or unavailable evidence remains UNKNOWN and that repository content is never executed. These are meaningful behavioral guarantees. It does not cover other behaviors such as side effects or failure modes, but the core safety and uncertainty handling are disclosed.

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 two sentences with no filler. It front-loads the core extraction/selection behavior and then adds the two most important behavioral caveats: UNKNOWN handling and non-execution of repository content. Every clause 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?

For a tool with six parameters and no output schema or annotations, the description is not fully complete. It explains the overall pipeline and key safety behavior but leaves unclear the exact meaning of 'fields,' the return shape, and how the pinned repository parameters interact with paper extraction. Still, it provides enough orientation for a competent agent to start using 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?

Schema description coverage is 0%, so the description must compensate. It does add useful meaning for the repository parameters by calling them an 'exact pinned repository revision' and for the question by referring to 'query intent.' However, it does not explain the 'fields' parameter or clarify the relationship between fields and the 'bounded fact set,' leaving a notable gap.

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 states a specific multi-step operation: extract a bounded query-independent fact set from a paper (and optional pinned repository revision), then select facts using the query intent. This clearly conveys the tool's function and distinguishes it from simpler extraction tools, though it does not explicitly name sibling tools.

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 implies when to use the tool: when a query-driven, bounded evidence reconstruction from a paper and optionally a pinned repository is needed. However, it provides no explicit when-to-use versus alternative tools, no exclusions, and no guidance on choosing between this and related siblings like extract_paper_facts or verify_claim.

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