Skip to main content
Glama

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Ask a short question

ask
Read-only

A question whose answer is a word or a value, answered from this account's workbooks and programs without starting a run: 'Is Moderna NASDAQ:MRNA a biotech company with public float above $5B?', 'What is Alterity Therapeutics' lead program?'. answer is yes, no, unsure, invalid_premise (what the question names is not there: no such company, or a name and ticker that are two different companies) or the value asked for. Amounts are compared in code against the figure a program returned (claims says which, as of when); sources cites each program run and workbook section the answer rests on. It answers unsure rather than guess when the evidence does not settle it. Give context to have it answer from your own text instead, among options if you pass them. Reads only; programs it runs are billed to this account.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNoText the answer must rest on — a study's abstract, a clinical note, a policy. Given, nothing is looked up: no program, no workbook, no search, and `sources` cites only this text. At most 60,000 characters.
optionsNoThe answers you take, e.g. ["yes", "no", "maybe"]: `answer` is one of them, or `unsure` when ask is not sure enough of any; `probabilities` gives each. Only with `context`.
questionYesThe question, in your own words.
llm_modelNoThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
skip_cacheNoRead the workbooks, outlines and programs afresh for this question, setting aside what ask has kept for this account — for just after a workbook or an outline changed. Off by default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Text the answer must rest on — a study's abstract, a clinical note, a policy. Given, nothing is looked up: no program, no workbook, no search, and `sources` cites only this text. At most 60,000 characters.",
+  "type": "string"
+}
    • addedInput schema / properties / options
      Added value: +{
+  "description": "The answers you take, e.g. [\"yes\", \"no\", \"maybe\"]: `answer` is one of them, or `unsure` when ask is not sure enough of any; `probabilities` gives each. Only with `context`.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 40,
+  "minItems": 2,
+  "type": "array"
+}
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations establish read-only/open-world/non-idempotent, and the description adds substantial context on top: the exact answer vocabulary including 'unsure' and 'invalid_premise', the refusal-to-guess policy, that amounts are compared in code against a program's returned figure, and that any programs run are billed to the account. This is rich behavioral disclosure well beyond the annotations.

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 core purpose is front-loaded before the mechanics, and most sentences carry real information (answer values, sources, billing). It is a dense single paragraph with some heavy nesting, costing a point on readability, but little is wasted.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so: it names `answer`, `claims`, `sources`, and `probabilities`. Combined with the mode and billing notes, an agent has everything needed to call it correctly.

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 description coverage is 100%, so the schema already documents every parameter, including the context character limit and the options/answer relationship. The description reinforces the context-vs-options interplay but adds little syntax or format beyond what the schema provides, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource (answers a short word/value question) with concrete examples and a clear source scope (this account's workbooks and programs, no run started). The behavior is easy to grasp. It does not, however, explicitly differentiate itself from the sibling 'answer_question', which by name sounds overlapping, so it falls short of a 5.

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?

It clearly frames the operating modes: default lookup from workbooks/programs, or 'give context to have it answer from your own text instead, among options if you pass them.' That route selection is useful. It stops short of telling the agent when to prefer this tool over siblings like answer_question or search_workbooks, so no explicit alternatives/exclusions are given.

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

All hedwigai toolsInspect
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