BGPT Scientific Data

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

No annotations provided, so description carries full burden. Successfully discloses cost model ($0.02/if found, free if not), authentication requirements (Stripe subscription ID), and return structure (25+ metadata fields or error).

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?

Uses structured docstring format (Args/Returns) that efficiently organizes information. Every sentence earns its place: example DOI, cost warning, and field enumeration are all high-value. Minor verbosity from 'Optional:' label and URL is acceptable.

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?

Comprehensive for a lookup tool: covers inputs, outputs (despite presence of output schema), pricing, and auth. Minor gap in error condition details beyond 'not found', but adequate given complexity.

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%, requiring full compensation. Description excellently documents both parameters: provides working DOI example with format hint, explains api_key purpose and registration URL, and notes optionality.

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?

Clear specific verb 'Look up', resource 'paper', and scope 'by its DOI'. Implicitly distinguishes from sibling 'search_papers' (ID-based lookup vs. general search).

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?

Provides crucial usage context via cost disclosure ('Costs $0.02 if found'), implying use when specific DOI is known. Lacks explicit reference to 'search_papers' as alternative for non-DOI queries.

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?

No annotations are provided, so the description carries the full burden. It successfully discloses the cost model (free tier + paid tier at $0.01/result), language constraints, and output structure (listing 25+ metadata fields). It does not mention rate limits or caching behavior, but covers the critical behavioral aspects of a paid search API.

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?

Uses a structured docstring format (Args/Returns) that front-loads the purpose statement. Every sentence adds value: parameter constraints, billing warnings, and output field summaries. No filler or tautology despite the comprehensive coverage.

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?

Despite 0% schema coverage and no annotations, the description comprehensively covers all 4 parameters, explains the billing model (which annotations might have covered), and summarizes the return values. The presence of an output schema reduces the need for detailed return documentation, but the provided summary enhances usability without redundancy.

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 by documenting all 4 parameters in the Args section: 'query' includes an example and format guidance ('CRISPR gene editing efficiency'), 'num_results' specifies range (1-100), default (16), and billing implications, 'days_back' explains the filtering logic, and 'api_key' identifies it as a Stripe subscription ID with a source URL.

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 clear, specific statement: 'Search BGPT's database of scientific papers by keyword.' It identifies the action (Search), the resource (BGPT's database of scientific papers), and the mechanism (by keyword). No siblings exist to differentiate from, but the scope is precisely defined.

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?

Provides clear usage constraints: 'Short, concise queries are best,' 'English language only,' and crucial billing guidance ('First 50 results are free, then billed at $0.01/result'). This helps the agent decide result count and query formulation. Lacks explicit 'when not to use' statements, but no siblings exist to contrast against.

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