BGPT - Scientific Paper Search

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

Beyond the read-only and idempotent annotations, the description adds the return envelope behavior (found status, paper in result, not-found message) and explains output_format options. It also notes that a found paper counts as one result, which is useful context.

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 well-structured with a clear purpose sentence, an Args section, and a Returns section. It is concise and information-dense without unnecessary words.

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 simple lookup tool with two parameters and an output schema, the description covers the essential operational details: what it does, how to specify parameters, and what the return envelope looks like. The output schema presumably handles the paper structure, so no need to detail that here.

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 schema has no descriptions for parameters, but the description fully documents both: doi with an example, and output_format with its three possible values and default. This fully compensates for the 0% schema coverage.

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 looks up a single paper by DOI, which is a specific verb+resource. However, it does not explicitly contrast with the sibling search_papers, so it doesn't fully distinguish alternatives.

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?

Usage is implied: use this when you have a DOI for a single paper. There is no explicit guidance on when not to use it or when to prefer the sibling search_papers, so it only partially addresses alternatives.

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

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

Despite annotations already indicating read-only and idempotent behavior, the description adds valuable context: 'First 50 results are free, then metered per result for paid users' and describes the return envelope structure ('papers with claims, experiments, exact results, demonstrated scope, limitations, and provenance'). This goes beyond the annotations and helps the agent understand cost and output shape.

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 well-structured with an opening sentence, an Args block, and a Returns block. Every sentence adds value, and the content is proportionally detailed for the tool's complexity. No fluff or redundancy.

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 output schema exists and the description covers all parameters, return structure, usage constraints, and cost behavior, the tool documentation is complete. The description is self-sufficient for an agent to select and invoke the tool correctly, even with four parameters and no schema descriptions.

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?

With 0% schema description coverage, the description fully compensates. The Args section explains each parameter thoroughly: query (short, concise, English only, use days_back/num_results instead of adding filters), num_results (range and cost), days_back (recency filter), and output_format (three options and their meanings). This provides all necessary semantics for correct invocation.

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 'Search claim-level evidence extracted from full-text scientific papers.' This specifies the verb (search), resource (claim-level evidence from full-text papers), and distinguishes the tool from the sibling lookup_paper by emphasizing claim-level extraction. The purpose is unambiguous and specific.

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 gives clear usage context, such as 'SHORT, concise queries are best. English language only. Use days_back and num_results instead of adding years or filters to the query.' However, it does not explicitly contrast with the sibling tool lookup_paper or state when to prefer one over the other. This prevents a score of 5, but the guidance is clear enough for a 4.

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