Skip to main content
Glama

JYOTINT Sealed Forecasts

get_regrade_kit

The grade-it-yourself kit: inputs to recompute the record's Brier (calibration), named-mechanism specificity, AND Information Yield under YOUR OWN verdicts — plus the one-step stress-test recipes (harsh-verdicts, externally-adjudicated-only, estimative-worst-case, …). Each call carries its verbatim claim/outcome, the operator's p + verdict to override, and the surprise_bits / 1-in-N inputs. A base rate scores 0 on specificity and 0 bits on IY. Pass an optional id for one call's row; omit for the recipes + usage + count.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoOptional advisory id for one call's regrade row.

TDQS

A4.4/5.0
Behavior4/5

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

No annotations present, but the description details what each call returns (claim/outcome, p, verdict, surprise_bits, 1-in-N) and mentions base rate behavior. It does not cover authorization or side effects, but as a read-only 'kit', this is sufficient.

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?

The description is detailed but slightly verbose with multiple clauses. It front-loads the purpose and efficiently packs information, though a more structured list could improve readability.

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?

Given no output schema and the tool's complexity, the description covers the input behavior, what each call carries, and base rate outcomes. It lacks details on output format but is reasonably complete for practical use.

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

Parameters5/5

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

The description adds significant context to the single parameter 'id', explaining that omitting it yields recipes/usage/count while including it gives a specific call's row. This goes beyond the schema's minimal description.

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?

The description clearly states the tool provides inputs to recompute Brier, specificity, and Information Yield under custom verdicts, including stress-test recipes. It distinguishes from sibling tools like get_calibration_and_integrity which likely provide default calculations.

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 description gives guidance on using the optional 'id' parameter (pass for one call's row, omit for recipes/usage/count). However, it does not explicitly compare to alternatives or state when not to use this tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools have clearly distinct purposes (fetch one forecast vs. list open calls vs. search), but neural_search and search_sealed_forecasts both retrieve from the same corpus, and ask_the_record overlaps slightly with neural_search for site-copy questions. Descriptions mitigate ambiguity, but a few boundaries require careful reading.

Naming Consistency4/5

The dominant pattern is get_<noun> (get_advisory, get_map, get_luck_test), with list_open_calls, search_sealed_forecasts, ask_the_record, and neural_search as deviations. All names are lowercase snake_case and readable, but the verb prefixes are not perfectly uniform.

Tool Count5/5

With 13 tools, the server is well-scoped for a specialized sealed-forecast corpus. Each tool addresses a distinct analytical or retrieval need, and the count fits comfortably in the ideal range without feeling bloated or thin.

Completeness5/5

The tool surface covers the full lifecycle of interacting with the corpus: search, retrieve, list, inspect stats, verify integrity, regrade, visualize, and ask questions. The append-only nature means no update/delete tools are needed, so the set is complete for its stated purpose.

Resources