Skip to main content
Glama

ontology_diff

Compare domain ontology between two git revisions to reveal added, removed, or changed concepts. Tracks vocabulary evolution across commits and helps identify naming inconsistencies in pull requests.

Instructions

Compare the domain ontology between two git revisions — shows concepts that were added, removed, or changed. Useful for understanding how the project's vocabulary evolved across commits or for reviewing whether a PR introduced naming inconsistencies.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceNoGit ref to diff from (default: HEAD~5)

Implementation Reference

  • Schema definition for ontology_diff tool: defines mcpName, label, description, promptSnippet, and parameters (optional 'since' string defaulting to HEAD~5).
    {
      mcpName: "ontology_diff",
      label: "Ontology Diff",
      description:
        "Compare the domain ontology between git revisions — shows concepts " +
        "added, removed, or changed.",
      promptSnippet:
        "ontomics_ontology_diff: diff domain vocabulary across git revisions",
      parameters: Type.Object({
        since: Type.Optional(
          Type.String({
            description: "Git ref to diff from (default: HEAD~5)",
          }),
        ),
      }),
    },
  • Registration loop that iterates over toolDefs() and calls pi.registerTool for each, including ontology_diff. The execute handler delegates to an MCP subprocess (ontomics serve) via callTool.
    for (const def of toolDefs()) {
      pi.registerTool({
        name: `ontomics_${def.mcpName}`,
        label: def.label,
        description: def.description,
        promptSnippet: def.promptSnippet,
        promptGuidelines: [
          "Use ontomics tools BEFORE grep/glob for semantic codebase questions.",
        ],
        parameters: def.parameters,
        async execute(_toolCallId, params, _signal, onUpdate, _ctx) {
          onUpdate?.({
            content: [{ type: "text", text: `Querying ontomics: ${def.mcpName}...` }],
          });
          try {
            const mcp = await getClient();
            const text = await mcp.callTool(def.mcpName, cleanArgs(params));
            return { content: [{ type: "text", text }] };
          } catch (err) {
            throw new Error(
              `ontomics ${def.mcpName} failed: ${err instanceof Error ? err.message : String(err)}`,
            );
          }
        },
      });
    }
  • The execute handler for ontology_diff (and all registered tools). It calls the external ontomics MCP server over stdio using McpClient.callTool, passing the tool name and cleaned arguments.
    async execute(_toolCallId, params, _signal, onUpdate, _ctx) {
      onUpdate?.({
        content: [{ type: "text", text: `Querying ontomics: ${def.mcpName}...` }],
      });
      try {
        const mcp = await getClient();
        const text = await mcp.callTool(def.mcpName, cleanArgs(params));
        return { content: [{ type: "text", text }] };
      } catch (err) {
        throw new Error(
          `ontomics ${def.mcpName} failed: ${err instanceof Error ? err.message : String(err)}`,
        );
      }
    },
  • McpClient class that communicates with the ontomics binary via JSON-RPC 2.0 over stdio. Used by the execute handler to call the ontology_diff tool on the external server.
    class McpClient {
      private proc: ChildProcess;
      private rl: ReadlineInterface;
      private nextId = 1;
      private pending = new Map<
        number,
        { resolve: (v: unknown) => void; reject: (e: Error) => void }
      >();
    
      private constructor(proc: ChildProcess) {
        this.proc = proc;
        this.rl = createInterface({ input: proc.stdout! });
        this.rl.on("line", (line: string) => this.onLine(line));
        proc.stderr?.on("data", () => {});
      }
    
      static async start(binaryPath: string, cwd: string): Promise<McpClient> {
        const proc = spawn(binaryPath, ["serve"], {
          cwd,
          stdio: ["pipe", "pipe", "pipe"],
        });
        const client = new McpClient(proc);
        await client.request("initialize", {
          protocolVersion: "2024-11-05",
          capabilities: {},
          clientInfo: { name: "pi-ontomics", version: "1.0.0" },
        });
        client.notify("notifications/initialized", {});
        return client;
      }
    
      async callTool(
        name: string,
        args: Record<string, unknown>,
      ): Promise<string> {
        const result = (await this.request("tools/call", {
          name,
          arguments: args,
        })) as { content?: Array<{ text?: string }> };
        const text = result.content?.[0]?.text ?? JSON.stringify(result);
        return text;
      }
    
      dispose(): void {
        this.proc.kill();
        this.rl.close();
      }
    
      get alive(): boolean {
        return !this.proc.killed && this.proc.exitCode === null;
      }
    
      private request(method: string, params: unknown): Promise<unknown> {
        const id = this.nextId++;
        return new Promise((resolve, reject) => {
          this.pending.set(id, { resolve, reject });
          this.write({ jsonrpc: "2.0", id, method, params });
        });
      }
    
      private notify(method: string, params: unknown): void {
        this.write({ jsonrpc: "2.0", method, params });
      }
    
      private write(msg: unknown): void {
        this.proc.stdin!.write(JSON.stringify(msg) + "\n");
      }
    
      private onLine(line: string): void {
        if (!line.trim()) return;
        try {
          const msg = JSON.parse(line) as {
            id?: number;
            result?: unknown;
            error?: { message: string };
          };
          if (msg.id != null && this.pending.has(msg.id)) {
            const { resolve, reject } = this.pending.get(msg.id)!;
            this.pending.delete(msg.id);
            if (msg.error) reject(new Error(msg.error.message));
            else resolve(msg.result);
          }
        } catch {
          // ignore non-JSON lines (e.g. stderr leaks)
        }
      }
    }
Behavior2/5

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

No annotations are provided, so the description bears full transparency responsibility. It only mentions comparing revisions and showing changes, but does not disclose prerequisites (e.g., git availability), performance, or output format. Minimal behavioral insight.

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?

The description consists of two sentences, with the primary action front-loaded. No redundant or extra information, every sentence adds value.

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?

Given no output schema and moderate complexity, the description lacks details on the output format (list vs diff). It mentions 'shows concepts' but not how they are presented. Siblings imply more context might be needed, but description is adequate for basic use.

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 100% for the single parameter 'since', which has a clear description in the schema. The tool description does not add extra meaning beyond what the schema provides, so baseline 3 is appropriate.

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 clearly states the tool compares domain ontology between two git revisions, showing added, removed, or changed concepts. This is a specific verb and resource, and distinguishes from sibling tools like list_concepts or concept_map.

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 explicitly states it is useful for understanding vocabulary evolution and PR review, providing clear usage context. It does not mention when not to use or alternative tools, but the context is strong enough for a 4.

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/EtienneChollet/ontomics'

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