semantic_scholar_recommendations

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

The annotations already declare readOnlyHint, openWorldHint, and idempotentHint, but the description adds substantial behavioral context beyond those: unknown seed IDs raise a not-found error, unkeyed requests are throttled to 1 req/s, 429/502/503 responses retry automatically with backoff, and the default output is Markdown. No contradiction with annotations.

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 front-loaded with the core purpose and then efficiently covers usage, alternatives, errors, rate limits, and output format in a compact paragraph. Every sentence adds operational value, with no repetition 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 has no output schema and a nested parameter object, the description is remarkably complete. It explains the input requirements, the meaning of the main parameters, the sibling tool to use for richer steering, error behavior, throttling/retry, and how to switch between Markdown and raw JSON output.

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?

Despite the context showing 0% schema description coverage for the single top-level param, the description compensates thoroughly. It explains paper_id with a concrete example, clarifies limit as an upper bound, defines from_pool options ('recent' vs 'all-cs'), and explains response_format values. Only the deprecated api_key is not mentioned, but that is adequately covered in the schema.

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 opens with a specific verb and resource: 'Get paper recommendations based on a seed paper.' It clearly distinguishes itself from the sibling tool by explicitly directing multi-example steering to semantic_scholar_multi_recommend, and it explains the candidate pool options.

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?

It gives concrete usage guidance: provide a known paper_id, use from_pool to choose the candidate set, and set limit. It explicitly names the alternative tool for multi-example scenarios. It also covers error handling and response format selection, making when-to-use very clear.

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