Skip to main content
Glama
yangkyeongmo

MCP Server for Apache Airflow

by yangkyeongmo

patch_pool

Modify Apache Airflow pool configurations to adjust task execution capacity and resource allocation.

Instructions

Update a pool

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pool_nameYes
slotsNo
descriptionNo
include_deferredNo

Implementation Reference

  • Registration of the patch_pool tool (and others) via get_all_functions, which returns a list of tuples (handler, name, description, read_only) for MCP tool registration.
    def get_all_functions() -> list[tuple[Callable, str, str, bool]]:
        """Return list of (function, name, description, is_read_only) tuples for registration."""
        return [
            (get_pools, "get_pools", "List pools", True),
            (get_pool, "get_pool", "Get a pool by name", True),
            (delete_pool, "delete_pool", "Delete a pool", False),
            (post_pool, "post_pool", "Create a pool", False),
            (patch_pool, "patch_pool", "Update a pool", False),
        ]
  • The async handler function implementing the patch_pool tool. It constructs a Pool object with provided optional updates and calls the Airflow PoolApi to patch the pool, returning the response as text.
    async def patch_pool(
        pool_name: str,
        slots: Optional[int] = None,
        description: Optional[str] = None,
        include_deferred: Optional[bool] = None,
    ) -> List[Union[types.TextContent, types.ImageContent, types.EmbeddedResource]]:
        """
        Update a pool.
    
        Args:
            pool_name: The pool name.
            slots: The number of slots.
            description: The pool description.
            include_deferred: Whether to include deferred tasks in slot calculations.
    
        Returns:
            The updated pool details.
        """
        pool = Pool()
    
        if slots is not None:
            pool.slots = slots
    
        if description is not None:
            pool.description = description
    
        if include_deferred is not None:
            pool.include_deferred = include_deferred
    
        response = pool_api.patch_pool(pool_name=pool_name, pool=pool)
        return [types.TextContent(type="text", text=str(response.to_dict()))]
Behavior1/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but offers minimal information. 'Update a pool' suggests a mutation operation but doesn't disclose whether this requires special permissions, what happens to existing pool settings not mentioned, whether the operation is idempotent, or what the typical response looks like. For a mutation tool with zero annotation coverage, this represents a significant transparency gap.

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 maximally concise at just three words. While this represents under-specification rather than ideal conciseness, from a pure structural perspective, there's no wasted language or unnecessary elaboration. Every word serves a purpose, even if that purpose is insufficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 4 parameters, 0% schema description coverage, no annotations, and no output schema, the description is completely inadequate. It doesn't explain what a 'pool' is in this system, what aspects can be updated, what the typical response contains, or any behavioral characteristics. The description fails to provide the contextual information needed to use this tool effectively.

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

Parameters1/5

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

The description provides zero information about parameters, while the schema has 0% description coverage. With 4 parameters (pool_name, slots, description, include_deferred) completely undocumented in both schema and description, users have no guidance on what these parameters mean, their expected formats, or how they affect the update operation. The description doesn't compensate for the schema's lack of parameter documentation.

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

Purpose2/5

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

The description 'Update a pool' is a tautology that restates the tool name 'patch_pool' without adding meaningful specificity. It doesn't clarify what aspects of a pool are updated or what 'pool' refers to in this context. While it includes a verb ('Update') and resource ('pool'), it lacks the specificity needed to distinguish this from sibling tools like 'post_pool' or 'delete_pool'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There are multiple pool-related tools in the sibling list (post_pool, delete_pool, get_pool, get_pools), but the description offers no differentiation. It doesn't mention prerequisites, appropriate contexts, or when this tool should be preferred over other pool operations.

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/yangkyeongmo/mcp-server-apache-airflow'

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