Election Index

Pollster track record

pollster

Read-only

A pollster's final published poll before each election we hold a certified result for, set against that result: share per party or candidate, error in points, mean absolute error, and the error on the winner's margin. Figures come from the pollster's own release or a registry, never an aggregator. Measured facts, not grades: nothing is ranked. Answers "How accurate was Novus in Sweden 2026?". Give a pollster id or name.

Input Schema

Name	Required	Description	Default
`pollster`	Yes	Pollster id or name, e.g. "novus" or "Verian"

Output Schema

Name	Required	Description	Default
`meta`	Yes	What this answer was built from; cite dataset_version
`result`	Yes	The pollster and its final polls, each with against_result (rows, mean_abs_error, margin_error, margin_towards: the count’s name for the contestant the poll leaned to, margin_towards_label: as readers know it, leader_same_as_result) or not_comparable

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

addedOutput schema / properties / meta / properties / doi

Added value: +{
+  "description": "Zenodo concept DOI: the latest archived release",
+  "type": "string"
+}

Changed1 schema field changedNov 3, 2026
- addedOutput schema / properties / meta / properties / copyright
```
Added value: +{
+  "description": "Rights holder",
+  "type": "string"
+}
```

Changed1 schema field changedOct 25, 2026

changedOutput schema / properties / result / description

Previous value: -"The pollster and its final polls, each with against_result (rows, mean_abs_error, margin_error and margin_towards, leader_same_as_result) or not_comparable"New value: +"The pollster and its final polls, each with against_result (rows, mean_abs_error, margin_error, margin_towards: the count’s name for the contestant the poll leaned to, margin_towards_label: as readers know it, leader_same_as_result) or not_comparable"

AddedOct 25, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Beyond readOnlyHint/openWorldHint the description adds real behavioral substance: the data comes from the pollster's own release or a registry and never an aggregator, and results are measured facts with no ranking or grading. It does not say what happens when a pollster has no certified-result history or the name is ambiguous, which is the remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: scope, then metrics, then provenance, then the disambiguating 'measured facts, not grades', then the example question. The metric list ('error in points, mean absolute error, and the error on the winner's margin') is slightly compressed, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't enumerate return fields, and it still previews them usefully alongside provenance guarantees. The only incompleteness is failure/edge behavior for unknown pollsters or pollsters lacking certified results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single required 'pollster' field already documented with examples ("novus", "Verian"). The description's 'Give a pollster id or name' merely echoes that id-or-name flexibility, adding no new semantics such as matching behavior or ambiguity handling.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names the exact resource (a pollster's final published poll before each election with a certified result) and the exact comparison being produced (poll vs. result, with per-party share, error, MAE, winner-margin error). Nothing here overlaps with siblings like election_status or next_election, so an agent can route to it confidently.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The sample question 'How accurate was Novus in Sweden 2026?' plus 'Give a pollster id or name' gives clear usage context and an input cue. It stops short of explicit when-not guidance or naming an alternative sibling (e.g., where to go for pollster-less poll data), so it sits just below the top band.

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

All Election Index tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?