Get a paper's real figure images — URLs, labels, and captions. Most biomedical papers have figures; arXiv papers often don't. Accepts an arXiv ID, PMC ID, or bioRxiv/medRxiv DOI.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | arXiv ID, PMC ID, or 10.1101/… DOI. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and openWorldHint. Description adds some behavioral context (returning real images, URLs, captions) but does not elaborate on edge cases like missing figures or error handling.
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?
Two sentences, front-loaded with purpose and output details. Every sentence adds value, no wordiness.
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?
No output schema exists, so description must compensate. It mentions returning URLs, labels, and captions, but lacks details on output structure or behavior when no figures found. Partial completeness.
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 coverage is 100% with one parameter. Description slightly elaborates on ID types (e.g., mentions bioRxiv/medRxiv) but adds little beyond schema description. Baseline 3 is appropriate.
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?
Description clearly states 'Get a paper's real figure images' with specifics on what is returned (URLs, labels, captions). It distinguishes from other paper-related tools by focusing on figures.
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 guidance on when to use (biomedical papers have figures, arXiv often don't) and acceptable ID types (arXiv, PMC, bioRxiv/medRxiv DOI). Lacks explicit when-not-to-use or alternatives, but context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: citation retrieval is split into inbound and outbound, paper data is divided into metadata, full text, figures, entities, and structure, with separate search and similarity tools. No overlap.
Most tools use snake_case, but there's a mix of 'get_' prefix (get_entities, get_figures, etc.) and direct action names (citations, references, search_papers). This is minor inconsistency; overall pattern is clear.
9 tools is well within the optimal range for a scientific paper server. Each tool adds unique value without overwhelming the interface.
The server covers the full lifecycle for paper retrieval: search, metadata, full text, figures, citations (both directions), entities, structure, and similarity. No obvious gaps for its read-only purpose.
