Skip to main content
Glama
Sign In
med-lit-mcp

med-lit-mcp

by junhewk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

review_article

Destructive

Record an include or exclude decision and reason for a single article in a medical literature review run, keeping screening choices auditable.

Instructions

Record the researcher's own include/exclude decision and reason for one article.

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": {
      "run_id": "<run_id>",
      "uid": "<uid>",
      "decision": "<decision>",
      "reason": "<reason>"
    },
    "name": "review_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
uidYes
reasonYes
run_idYesRun ID from start_search
decisionYes
criterionNoFor an exclude: the criterion code it rests on (E1, I2)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / criterion
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 4,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "For an exclude: the criterion code it rests on (E1, I2)",
+  "title": "Criterion"
+}
  2. First observedv0.1.1

TDQS

B3.3/5.0
Behavior2/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the description needn't repeat safety metadata. It adds only that the decision belongs to the researcher; it does not explain what the destructive write affects (run state, audit trail), whether a recorded decision can be revised, or what happens after the last article is reviewed.

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

Conciseness5/5

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

A single sentence with no filler; the subject (recording a decision) is front-loaded and every clause carries information.

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

Completeness3/5

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

With an output schema and annotations present, the description covers the core action adequately. It is still incomplete for a destructive, non-idempotent write: it omits the criterion parameter and gives no sense of downstream workflow effects.

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 40%, so the description should compensate. It names the decision and reason inputs and implies the article identifier, but never mentions the optional 'criterion' parameter that matters for excludes, nor the include/exclude enum values.

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?

The description states a specific verb (record) and resource (include/exclude decision and reason for one article). The qualifier 'researcher's own' distinguishes it from automated bulk operations such as record_screening_decisions, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is implied by 'researcher's own' and 'one article' – use this for a single manual review rather than bulk screening. There is no explicit statement of when to prefer it over record_screening_decisions, nor any prerequisites.

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

Deploy Server

Other Tools