Skip to main content
Glama

Midgard Finance drug data

Compare weight-loss efficacy

compare_efficacy
Read-only

The extracted weight-loss table for the named drugs, joined to trial design, one row per arm and timepoint.

Rows are NOT collapsed to one number per drug. The corpus holds several doses, timepoints and estimands per trial, and picking a single winner per drug would mean choosing between them here, silently and on the caller's behalf. The comparison is theirs to make; this returns the rows and the labels needed to make it correctly.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "drugs": "<drugs>"
    },
    "name": "compare_efficacy"
  }
}

Input Schema

NameRequiredDescriptionDefault
drugsYes
limitNo
metricNomean_weight_change_pct
estimandNo
timepoint_weeksNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedInput schema / properties / drugs / anyOf
      Removed value: -[
      -  {
      -    "items": {
      -      "type": "string"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / drugs / default
      Removed value: -null
    • addedInput schema / properties / drugs / items
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / drugs / type
      Added value: +"array"
    • changedInput schema / properties / limit / default
      Previous value: -40New value: +10
    • addedInput schema / required
      Added value: +[
      +  "drugs"
      +]
  2. First observed

TDQS

C2.6/5.0
Behavior3/5

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

Annotations already cover readOnly/non-destructive/closed-world, so the description's useful contribution is the no-collapse guarantee and the fact that dose, timepoint and estimand labels come back with the rows. However, for a tool with a default limit of 10 it says nothing about truncation behavior or ordering, which matters greatly here since a silently truncated row set would invalidate the caller's comparison.

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

Conciseness3/5

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

Front-loaded with the return shape, which is good, but roughly half the text is design rationale ('picking a single winner would mean choosing between them here, silently and on the caller's behalf') that reassures rather than instructs. The point could be made in one sentence instead of three.

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

Completeness2/5

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

With no output schema, five entirely undocumented parameters, and no statement of returned column names or formats, the definition leaves the agent guessing on the mechanics it needs to call correctly. The rationale about non-collapsed rows is the right idea but is not enough to make the call safely.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden, yet it names no parameter and explains no format or defaults. It gestures at the concepts ('several doses, timepoints and estimands per trial') but does not tell the agent what metric values exist, what estimand strings are valid, or what limit counts (rows, arms, trials).

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

Purpose3/5

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

The description states what the tool returns (an extracted weight-loss table for named drugs, joined to trial design, one row per arm and timepoint) but never states the action it performs, so the agent must infer 'fetch' from the name 'compare_efficacy'. It is recognizable as an efficacy-data retrieval tool but is not differentiated from siblings such as get_trajectory or get_trial, which plausibly return overlapping data.

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

Usage Guidelines2/5

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

There is no when-to-use guidance and no alternative named. The description never says how this relates to get_trajectory, get_trial, or search_drugs, nor whether drug names must be resolved via search_drugs first. Only an implicit usage stance is conveyed: use this when you want raw comparable rows rather than a single winner.

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.

Resources