Skip to main content
Glama

getTopLevelDeclarationNames

Extract top-level declaration names (functions, data types, type classes) from PureScript code or a file. Enables code analysis without requiring an IDE server, simplifying development tasks.

Instructions

List all main definitions in PureScript code: function names, data types, type classes, etc. Gets just the names (like 'myFunction', 'MyDataType'). Fast analysis without needing IDE server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNoPureScript code string.
filePathNoAbsolute path to the PureScript file. Only absolute paths are supported.

Implementation Reference

  • Handler function that implements getTopLevelDeclarationNames tool. Uses Tree-sitter to parse PureScript code, executes a custom query to capture names of various top-level declarations (functions, data types, classes, imports, signatures, instances, kind declarations), deduplicates, and returns as a JSON array of strings.
        "getTopLevelDeclarationNames": async (args) => {
            if (!treeSitterInitialized) throw new Error("Tree-sitter not initialized.");
            const code = await getCodeFromInput(args, true); // true for module-oriented
            const tree = purescriptTsParser.parse(code);
            const querySource = `
    [
      (function name: (variable) @name)
      (data name: (type) @name)
      (class_declaration (class_head (class_name (type) @name)))
      (type_alias name: (type) @name)
      (foreign_import name: (variable) @name)
      (signature name: (variable) @name)
      (class_instance (instance_name) @name)
      (kind_value_declaration name: (type) @name)
    ]
    `;
            const query = new Query(PureScriptLanguage, querySource);
            const captures = query.captures(tree.rootNode);
            const declarationNames = captures.map(capture => capture.node.text).filter(Boolean);
            // Deduplicate names
            const uniqueNames = [...new Set(declarationNames)];
            return { content: [{ type: "text", text: JSON.stringify(uniqueNames, null, 2) }] };
        },
  • index.js:602-613 (registration)
    Tool registration in TOOL_DEFINITIONS array, used by 'tools/list' MCP method to advertise the tool's name, description, and input schema to clients.
        name: "getTopLevelDeclarationNames",
        description: "List all main definitions in PureScript code: function names, data types, type classes, etc. Gets just the names (like 'myFunction', 'MyDataType'). Fast analysis without needing IDE server.",
        inputSchema: {
            type: "object",
            properties: {
                filePath: { type: "string", description: "Absolute path to the PureScript file. Only absolute paths are supported." },
                code: { type: "string", description: "PureScript code string." }
            },
            additionalProperties: false,
            description: "Exactly one of 'filePath' or 'code' must be provided."
        }
    },
  • JSON Schema defining the input parameters for the tool: exactly one of absolute filePath or inline code string.
    inputSchema: {
        type: "object",
        properties: {
            filePath: { type: "string", description: "Absolute path to the PureScript file. Only absolute paths are supported." },
            code: { type: "string", description: "PureScript code string." }
        },
        additionalProperties: false,
        description: "Exactly one of 'filePath' or 'code' must be provided."
    }
  • Helper function to retrieve PureScript code from tool arguments, supporting either absolute file path (reads file) or inline code string. Validates inputs and used by multiple AST tools including this one.
    async function getCodeFromInput(args, isModuleOriented = true) {
        if (isModuleOriented) {
            const hasFilePath = args && typeof args.filePath === 'string';
            const hasCode = args && typeof args.code === 'string';
    
            if ((hasFilePath && hasCode) || (!hasFilePath && !hasCode)) {
                throw new Error("Invalid input: Exactly one of 'filePath' or 'code' must be provided for module-oriented tools.");
            }
            if (hasFilePath) {
                if (!path.isAbsolute(args.filePath)) {
                    throw new Error(`Invalid filePath: '${args.filePath}' is not an absolute path. Only absolute paths are supported.`);
                }
                try {
                    return await fs.readFile(args.filePath, 'utf-8');
                } catch (e) {
                    throw new Error(`Failed to read file at ${args.filePath}: ${e.message}`);
                }
            }
            return args.code;
        } else { // Snippet-oriented
            if (!args || typeof args.code !== 'string') {
                throw new Error("Invalid input: 'code' (string) is required for snippet-oriented tools.");
            }
            return args.code;
        }
    }
Behavior3/5

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 that the tool performs 'Fast analysis' and works 'without needing IDE server', which are useful behavioral traits. However, it doesn't mention potential limitations like file size constraints, error handling, or performance characteristics beyond speed.

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 is efficiently structured in two sentences that each earn their place: the first states the core functionality and scope, the second adds important behavioral context about speed and server requirements. No wasted words.

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?

For a read-only analysis tool with no annotations and no output schema, the description provides adequate but minimal context. It explains what the tool does and some behavioral aspects, but doesn't describe the return format (e.g., array of strings) or potential edge cases, leaving gaps for the agent to infer.

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?

The schema has 100% description coverage, so the baseline is 3. The description doesn't add any parameter-specific information beyond what's in the schema (which already explains the 'filePath' and 'code' parameters and their mutual exclusivity).

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 specific action ('List all main definitions'), resource ('PureScript code'), and scope ('just the names'). It distinguishes from sibling tools like 'getTopLevelDeclarations' by specifying it only returns names, not full declarations.

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 provides clear context for when to use this tool ('Fast analysis without needing IDE server'), but doesn't explicitly state when not to use it or name specific alternatives. It implies usage for quick name extraction versus more detailed analysis tools.

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

Related 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/avi892nash/purescript-mcp-tools'

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