med-lit-mcp

Overview Schema Source Related Servers Discussions Admin

start_search

Search medical literature databases using an approved research question, create a project run, and resume it when the search status is running.

Instructions

Search the literature databases with an approved question; creates a run in the project. If search_status is 'running', call resume_search(run_id).

Input Schema

TableJSON Schema

Name	Required	Description
`project`	No	Project name from list_projects; may be omitted when only one project exists
`question_id`	Yes	From validate_question, after the researcher approved it
`wait_seconds`	No
`limit_per_source`	No	One-off override of the project's setting

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.1.5Oct 1, 2026
- addedInput schema / properties / limit_per_source / anyOf
```
Added value: +[
+  {
+    "maximum": 200,
+    "minimum": 1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
```
- changedInput schema / properties / limit_per_source / default
```
Previous value: -20New value: +null
```
- addedInput schema / properties / limit_per_source / description
```
Added value: +"One-off override of the project's setting"
```
- removedInput schema / properties / limit_per_source / maximum
```
Removed value: -200
```
- removedInput schema / properties / limit_per_source / minimum
```
Removed value: -1
```
- removedInput schema / properties / limit_per_source / type
```
Removed value: -"integer"
```
First observedv0.1.1Sep 29, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the agent knows this is a non-idempotent write. The description usefully adds that a run is created in the project and that a running search should be resumed rather than restarted, but says nothing about blocking/wait behavior despite a wait_seconds parameter.

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?

Two compact sentences; the primary action is front-loaded and the conditional resume guidance follows. No filler, though the resume rule is slightly compressed into the same breath as the main action.

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?

An output schema exists so return values need not be explained, and the description covers the write side effect and the alternate path for in-flight runs. It is nearly complete for a tool of this complexity; only the wait_seconds blocking semantics are unaddressed.

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 75%, so most parameters are already documented in the schema (project, question_id, limit_per_source). The description reinforces the 'approved question' precondition for question_id but adds no new semantics for wait_seconds or limit_per_source. Baseline 3 is appropriate.

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 ('Search the literature databases') plus a notable side effect ('creates a run in the project'). It differentiates from the sibling resume_search by naming it explicitly, though it doesn't distinguish from validate_question, which is the natural predecessor.

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?

Gives clear conditions: the question must be approved, and if search_status is 'running' the agent should call resume_search(run_id) instead. That routing rule is genuinely actionable. It stops short of stating prerequisites like validate_question completing first, which is left to the schema.

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