recommendations_for_paper

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

With no annotations, the description must disclose behavior. It mentions the ML recommendation engine, hinting at non-deterministic results, but does not explain result variability, potential delays, or that recommendations may change over time. It provides the pool options but lacks detail on what 'recent' means. No contradiction with annotations (none provided).

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 long, front-loaded with the purpose, and includes a key usage hint about pools. Every sentence contributes meaning without redundancy or fluff.

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 complexity (ML recommendation, 5 parameters, no output schema), the description covers the core functionality and pool options. However, it lacks details on output format (though response_format param exists), potential rate limits, or that it operates on a single paper per call. Still, it is sufficient for an agent to understand usage.

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 coverage is 100%, so parameters are already described in the schema. The tool description adds value by explaining the two pool options and the general recommendation purpose, going beyond what the schema alone provides (e.g., schema says 'recent' is default, description explains it's for 'latest papers'). This compensates for the lack of annotation context.

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: 'Get papers recommended as similar or related to a given paper, using Semantic Scholar's machine learning recommendation engine.' It distinguishes from siblings like paper_references (references) and paper_search (query-based) by specifying it's a recommendation engine. The two pool options further clarify scope.

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 use for discovering related papers but does not explicitly state when to prefer this over alternatives like paper_references or paper_search. It mentions pool choices but lacks guidance on when to use 'recent' vs 'all-cs' or when not to use the tool.

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