Skip to main content
Glama

research_project_create

Create a research project that persists across sessions. Returns a project_id for subsequent calls. Depth parameter controls exploration from overview (5 docs) to deep (20+ docs with adversarial verification).

Instructions

Create a persistent research project. Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions — open it days later with research_project_continue and you get every prior finding, hypothesis, and open gap. Depth controls how aggressively the synthesizer explores: overview (5 docs), standard (10 docs), deep (20+ docs with adversarial verification).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
userIdNoOwner user_id (matches memory userId).
nameYesShort project label.
questionYesThe central question to investigate.
depthNo"overview" | "standard" | "deep". Default "standard".

Implementation Reference

  • The handler function for research_project_create. Inserts a new research project into the 'research_projects' table with userId, name, question, and depth (defaulting to 'standard'), then returns the new project_id.
    const handleProjectCreate: McpToolHandler = async (args, ctx) => {
      const pool = (await ensureSchema(ctx)) as any;
      const userId = String(args.userId ?? ctx.userId);
      if (!userId) return err('userId required');
      const r = await pool.query(
        `INSERT INTO research_projects (user_id, name, question, depth)
         VALUES ($1,$2,$3,$4) RETURNING id`,
        [userId, String(args.name), String(args.question), String(args.depth ?? 'standard')],
      );
      return ok(asText({ success: true, project_id: r.rows[0].id, name: args.name, question: args.question, depth: args.depth ?? 'standard' }));
    };
  • The input schema definition for research_project_create. Defines the tool name, description, and inputSchema with properties: userId (string), name (string, required), question (string, required), depth (string, optional, 'overview'|'standard'|'deep').
      name: 'research_project_create',
      description: 'Create a persistent research project. Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions — open it days later with research_project_continue and you get every prior finding, hypothesis, and open gap. Depth controls how aggressively the synthesizer explores: overview (5 docs), standard (10 docs), deep (20+ docs with adversarial verification).',
      inputSchema: {
        type: 'object',
        properties: {
          userId: { type: 'string', description: 'Owner user_id (matches memory userId).' },
          name: { type: 'string', description: 'Short project label.' },
          question: { type: 'string', description: 'The central question to investigate.' },
          depth: { type: 'string', description: '"overview" | "standard" | "deep". Default "standard".' },
        },
        required: ['name', 'question'],
      },
    },
  • RESEARCH_TOOLS array entry registering the research_project_create tool. Includes group 'ai', the full definition, and links to the handleProjectCreate handler.
    export const RESEARCH_TOOLS: RegisteredTool[] = [
      {
        group: 'ai',
        definition: {
          name: 'research_project_create',
          description: 'Create a persistent research project. Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions — open it days later with research_project_continue and you get every prior finding, hypothesis, and open gap. Depth controls how aggressively the synthesizer explores: overview (5 docs), standard (10 docs), deep (20+ docs with adversarial verification).',
          inputSchema: {
            type: 'object',
            properties: {
              userId: { type: 'string', description: 'Owner user_id (matches memory userId).' },
              name: { type: 'string', description: 'Short project label.' },
              question: { type: 'string', description: 'The central question to investigate.' },
              depth: { type: 'string', description: '"overview" | "standard" | "deep". Default "standard".' },
            },
            required: ['name', 'question'],
          },
        },
        handler: handleProjectCreate,
      },
  • buildRegistry() combines RESEARCH_TOOLS (among others) into the full registry. This is where RESEARCH_TOOLS is imported and included.
    export function buildRegistry(): RegisteredTool[] {
      return [
        ...OPENCORE_TOOLS,
        ...JOURNAL_TOOLS,
        ...WRITE_TOOLS,
        ...RESEARCH_TOOLS,
      ];
    }
  • ensureSchema helper that lazily creates the research_projects (and related) tables on first call. Called by handleProjectCreate before inserting a new project.
    let schemaReady = false;
    async function ensureSchema(ctx: McpToolContext): Promise<unknown> {
      const pool = ctx.pool as { query: (sql: string, params?: any[]) => Promise<any> } | undefined;
      if (!pool) throw new Error('research tools require pool in McpToolContext');
      if (!schemaReady) {
        await pool.query(RESEARCH_SCHEMA_SQL);
        schemaReady = true;
      }
      return pool;
    }
Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses persistence across sessions, depth control with document counts, and that it returns a project_id. It could mention any limitations or authentication needs but is otherwise transparent.

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?

Three sentences with no wasted words. The key action and return value are front-loaded, and each sentence conveys essential information.

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?

Despite having no output schema, the description explicitly states the return value (project_id) and its role in subsequent calls. It covers all relevant aspects for a creation tool with four parameters.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds significant value by explaining the depth parameter's effect (overview=5 docs, standard=10, deep=20+ with adversarial verification), which goes beyond the schema enum.

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

Purpose5/5

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

The description begins with a clear verb+resource ('Create a persistent research project') and distinguishes itself from siblings like research_project_continue and research_project_list by emphasizing persistence and the project_id return value.

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?

The description explains that the returned project_id can be passed to subsequent research_* calls and details depth options. However, it does not explicitly state when not to use this tool or contrast it with alternatives like research_project_list.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/terrizoaguimor/celiums-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server