Skip to main content
Glama

Xcatcher — Recent X Posts

by io.github.lvpiggyqq

Create an X crawl task

create_crawl_task
Destructive

Create a crawl task for one or more X (Twitter) usernames. Side effects: creates a new task AND consumes points.

If points are insufficient, upstream returns HTTP 402 with PAYMENT-REQUIRED (quote). This tool surfaces it as error.code=PAYMENT_REQUIRED with payment_required payload so agents can request spending approval, top up, then retry safely.

Modes:

  • normal: Fast latest-post snapshot at scale (fresh-feed monitoring). Optimized for high-throughput batch retrieval.

  • deep: Deeper per-user collection/enrichment (typically slower; higher resource usage). Use when you need more than a quick latest-post snapshot.

Performance note: Normal mode is optimized for a small latest-post snapshot per handle. Actual completeness and latency depend on X availability, upstream limits, and network conditions. Batching: For very large sets, split users into batches. Suggested upper bound per task: 500 users (configurable via MAX_USERS_PER_TASK).

Reliability:

  • Use idempotency_key to make retries safe (avoid duplicate charges).

  • After creation, poll get_task_status every 5–10s until has_result=true.

  • Then call get_result_download_url (download still requires the same Bearer token).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNonormal = fast latest-post snapshot at scale; deep = deeper per-user collection (slower).normal
usersYesArray of X usernames (handles). You may include a leading '@'.
idempotency_keyNoOptional idempotency key for safe retries (recommended for agents).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

The description goes well beyond the annotations (which only say non-readonly, open-world, non-idempotent, destructive) by disclosing side effects (creates a task and consumes points), HTTP 402 payment behavior with error.code and payload details, and retry safety via idempotency_key. It also includes performance caveats and operational details like polling intervals, which are crucial for safe invocation.

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?

The description is longer than some but is well-structured into labeled sections (Modes, Performance note, Batching, Reliability), making it easy to scan. Each sentence contributes valuable operational information, with no gratuitous filler.

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?

The description covers the full lifecycle: creation, payment failure handling, mode selection, performance expectations, batching limits, and follow-up steps (polling and downloading). With an output schema present and rich annotations, the description is sufficient for an agent to invoke the tool correctly and handle common failure modes.

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?

The schema already covers all three parameters with 100% description coverage, including the mode enum and user array constraints. The description adds behavioral meaning: idempotency_key is recommended to avoid duplicate charges, and users should be batched with a MAX_USERS_PER_TASK upper bound of 500, enriching the schema's static definitions.

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 opens with 'Create a crawl task for one or more X (Twitter) usernames' – a specific verb ('create') and resource ('crawl task') – which clearly distinguishes it from sibling status, listing, and cancellation tools. It immediately conveys the tool's core function and differentiates from related tools.

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 strong contextual guidance: when to use normal vs. deep mode, batching guidance with a suggested upper bound of 500 users, and a reliability workflow that points to get_task_status and get_result_download_url. It does not explicitly state when not to use this tool, but the guidance is clear enough for an agent to select it appropriately.

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

All Xcatcher — Recent X Posts toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Every tool has a clearly distinct purpose, with explicit guidance for when to use accountless vs API-key variants. Even closely related tools like get_task_status and wait_for_task are differentiated by their polling behavior, so an agent can reliably select the correct one.

Naming Consistency4/5

Most tools follow a consistent verb_noun pattern in snake_case (create_crawl_task, get_task_status, list_crawl_tasks). The one exception is x402_topup, which places the protocol prefix before the verb, breaking the pattern slightly but still remaining readable.

Tool Count4/5

With 17 tools, the count is slightly above the typical 3-15 range, but the service supports two distinct payment paths (API-key and accountless x402), each requiring a parallel set of status/result tools. The count feels justified by the scope, with no obvious bloat.

Completeness5/5

The tool set covers the full lifecycle of creating, monitoring, retrieving, and managing crawl tasks, including both payment flows. It includes task creation, status polling, result preview/download, cancellation, listing, balance checks, and payment top-ups, leaving no critical gaps for the stated purpose.

Resources