Use before quoting a figure: this returns what stands behind it — the values, the control run, and the conditions that limit them. Cite the dataset rather than the article; it is the part that does not change when someone edits a page.
| Name | Required | Description | Default |
|---|---|---|---|
| dataset | Yes | Dataset URL or bare filename |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses that the return includes values, control run, and limiting conditions, and emphasizes dataset stability ('does not change when someone edits a page'). It does not mention error behavior, but for a getter this is acceptable.
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 two sentences, front-loaded with the primary use case ('Use before quoting a figure'), and every sentence adds value. There is no redundancy or filler.
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 single-parameter tool with no output schema or annotations, the description explains the return content (values, control run, conditions) and the proper context for use. It lacks details on error handling but is still fairly complete for a getter tool.
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 100% (the 'dataset' parameter is described as 'Dataset URL or bare filename'). The description adds no additional parameter syntax details, but reinforces that the dataset is the object to cite, which is helpful context. Baseline of 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?
The description clearly states the tool returns the measurement data behind a figure (values, control run, conditions). It distinguishes this from sibling tools like extract_citation and get_method by focusing on raw data retrieval.
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 explicitly tells the agent to use this tool before quoting a figure and to cite the dataset rather than the article. It gives clear context but does not explicitly name alternative tools or exclusion criteria.
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.
Most tools have clearly distinct purposes, such as single vs batch citation extraction. The only potential confusion is between list_measurements and get_measurement_data, both of which return measurement data; however, their descriptions indicate one lists available data and the other retrieves a specific figure's backing data.
Tool names predominantly follow a verb_noun pattern (extract_citation, install_extension, list_measurements). Two exceptions—adoption_stats and how_to_capture—deviate from this pattern, but they are still readable and not chaotic.
Ten tools is a reasonable scope for a specialized server covering citation extraction, measurements, capture guidance, and project status. No tool is redundant, and the count is neither too sparse nor overwhelming.
The server covers the main workflows: single/batch citation extraction, retrieving and listing measurement data, fetching reproducible methods, and obtaining capture setup instructions. Minor gaps exist, such as no tool for creating new measurements, but the domain is primarily read-only and contribution is handled through open_work.
