semantic_scholar_search_papers

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering safety and side-effect expectations. The description builds on this by adding search-specific behavioral details: boolean operators, quoted phrases, filter types, pagination via offset/limit, and default vs. JSON response format. It does not cover potential rate limits or error behaviors, but these are not critical for a read-only search tool when annotations already signal safety.

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 a single dense paragraph that front-loads the core purpose, then packs capabilities, limitations, alternatives, and output format into just a few sentences. Every clause earns its place; there is no fluff or repetition of schema field names. The structure flows logically from what → how → when-to-use-other-tools → output format.

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 (multiple filters, pagination, output formats) and the absence of an output schema, the description fully equips an agent to select and invoke it correctly. It covers input essentials, pagination behavior, alternative tools for edge cases, and return format. The schema and annotations cover parameter details and safety, so no critical gaps remain.

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?

The input schema already contains detailed descriptions for every parameter (e.g., year formats, limit bounds, query examples). The tool description adds meaningful context that is not fully in the schema: relevance ranking semantics, the availability of specific filter families, and that response_format='json' yields raw JSON. Although the description does not enumerate each parameter by name, the schema provides that, and the description enhances understanding of when and how to use them.

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+resource ('Search for academic papers') and immediately clarifies the scope: relevance-ranked keyword search over 200M+ papers. It distinguishes itself from sibling tools by explicitly naming alternatives (bulk_search, snippet_search, match_paper) and explaining when each is appropriate, leaving no ambiguity about its purpose.

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 explicit when-to-use guidance by stating that for sorted or very large result sets one should use semantic_scholar_bulk_search, for full-text search one should use semantic_scholar_snippet_search, and for resolving a single known title one should use semantic_scholar_match_paper. It also notes pagination limits (max 100 per call), which is key for correct invocation.

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