Skip to main content
Glama
Native Research MCP

Native Research MCP

by pipiwego

research_recover

Read-only

Recover interrupted research output using saved visible evidence and a model request that avoids new searches or page fetches.

Instructions

Recover from saved visible evidence. This operation uses a model request without search or fetch tools.

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": {
      "research_id": "<research_id>",
      "parent_revision": "<parent_revision>",
      "gap": "<gap>"
    },
    "name": "research_recover"
  }
}

Input Schema

NameRequiredDescriptionDefault
gapYes
research_idYes
parent_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior3/5

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

The description adds genuine behavior beyond the annotations: the operation performs a model request and does not use search or fetch tools, which tells the agent no new external evidence will be gathered. It does not disclose cost/latency, what happens to prior revisions, or side effects, and the word 'Recover' sits in mild tension with readOnlyHint=true without being an outright contradiction. Useful but thin for a three-parameter operation.

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 short sentences with no filler, and the core statement leads. It is efficient, though efficiency here partly reflects under-specification rather than disciplined editing.

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?

For a tool with three required, wholly undocumented parameters, no output schema, and a non-idempotent model-backed operation, the description should explain the parameters and the result at least at a high level. It covers neither, so an agent cannot confidently invoke it correctly.

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 all three required parameters (research_id, parent_revision, gap) carry no documented meaning anywhere. The description never mentions them, leaving especially opaque how 'parent_revision' should be chosen and what text belongs in 'gap'. This is the definition's largest gap.

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 verb 'Recover' and the object 'saved visible evidence' are stated, but what is actually recovered (a revision? a research run? a summary?) is never made concrete. The second sentence clarifies the execution mode rather than the purpose. An agent can guess this relates to the research_* siblings but cannot tell precisely what the operation produces.

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 statement of when to call this versus research_start, research_evidence, or research_status. The phrase 'without search or fetch tools' hints at a contrast with search-based flows but never converts that into a selection rule. The agent must infer the trigger condition entirely.

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