BGPT - Scientific Paper Search

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

With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it specifies cost implications ('Costs $0.02 if found, free if not'), error handling ('or an error if not found'), and output details. It also hints at authentication (api_key for paid access) and rate/access limits via the cost note. No contradictions exist.

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, followed by structured sections for Args and Returns. Every sentence adds value: the first states the action, the Args explain parameters, and the Returns detail output and cost/error behavior. No wasted 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?

Given the tool's moderate complexity (2 parameters, no annotations, but with output schema), the description is complete. It covers purpose, parameters, output content, cost, error handling, and implies authentication. With an output schema present, it appropriately doesn't need to detail return structure further.

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 fully. It does so by explaining both parameters: 'doi' is described with an example and purpose, and 'api_key' is clarified as optional for paid access with a URL for obtaining it. This adds essential meaning beyond the bare 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 clearly states the specific action ('Look up a single paper') and resource ('by its DOI'), distinguishing it from the sibling 'search_papers' which implies broader searching rather than direct lookup by identifier. The purpose is precise and unambiguous.

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 usage context by specifying it's for looking up a single paper by DOI, which naturally distinguishes it from 'search_papers' (likely for broader queries). However, it does not explicitly state when not to use this tool or name alternatives beyond the sibling, nor does it mention prerequisites like authentication needs beyond the optional api_key.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the tool requires a query, has billing implications (first 50 results free, then $0.01/result for paid users), supports optional API key for paid access, and returns papers with specific metadata fields. It doesn't mention rate limits or authentication requirements beyond the API key.

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 clear sections (Args, Returns) and front-loaded with the core purpose. Most sentences earn their place by providing essential information, though the billing details could be slightly more concise. Overall, it's appropriately sized for a 4-parameter tool with complex behavior.

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 (search functionality with billing implications), no annotations, and the presence of an output schema, the description is complete enough. It covers purpose, usage, parameters, behavioral traits, and return content. The output schema existence means the description doesn't need to detail return values, which it appropriately references without over-explaining.

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?

Given 0% schema description coverage, the description fully compensates by providing detailed semantic information for all parameters: query (search terms, format guidance), num_results (range, default, billing implications), days_back (time filtering), and api_key (optional, purpose, how to obtain). This adds substantial value beyond the bare 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 clearly states the tool searches BGPT's database of scientific papers by keyword, providing a specific verb ('search') and resource ('scientific papers'). It distinguishes from the sibling tool 'lookup_paper' by focusing on keyword-based searching rather than direct lookup, though the distinction could be more explicit.

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 clear context on when to use this tool (searching by keyword) and includes some guidance on query formulation (short, concise, English-only). It mentions not to include years or filters in the query, directing users to use other parameters instead. However, it doesn't explicitly contrast with the sibling tool 'lookup_paper' or provide when-not-to-use scenarios.

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