Skip to main content
Glama
Sign In
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

research_events

Read paged events for a research job by job_id to track its progress. Use limit and cursor to continue through results.

Instructions

Read research job events. Reads a page of events for one of the caller's research jobs, by job_id. limit is 1 to 100 (default 50); pass next_cursor back as cursor to continue, with has_more showing whether more remain. Each event has sequence, type (such as source_fetched or round_completed), timestamp, message and source_id.

Input Schema

NameRequiredDescriptionDefault
limitNoPage size from 1 through 100; default 50
cursorNoSigned event cursor
job_idYesResearch job ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.12

TDQS

A3.5/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden. It does disclose pagination mechanics (cursor round-trip, has_more) and the shape of each event, which is genuinely useful. But it omits the safety/behavioral profile an unannotated read tool needs: it does not say whether events are immutable, whether reads are rate-limited, whether results are eventually consistent for in-flight jobs, or how far back events are retained.

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 tight sentences, front-loaded with the verb+resource, then pagination, then event shape. No filler, and the detail that would otherwise be missing (event fields) is packed into the final clause because there is no output schema.

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

Completeness4/5

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

With no output schema, the description compensates by enumerating the event fields (sequence, type, timestamp, message, source_id) and gives example type values, plus complete pagination instructions. The remaining gap is upstream context — where job_id comes from and how event types relate to job phases.

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 the baseline is 3. The description earns above baseline by explaining cursor semantics that the schema alone does not: the returned `next_cursor` is fed back as the `cursor` parameter to continue paging, which maps a response field to an input field. limit is restated consistently with the schema rather than extended.

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

Purpose4/5

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

"Read research job events" names a specific verb and resource, and the following sentence clarifies scope (a page of events for one of the caller's research jobs, keyed by job_id). It is clearly distinct from research_start/research_cancel, though it never explicitly contrasts itself with the closest sibling, research_status.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the agent can infer this is for inspecting the event log of an existing job, and the pagination instruction tells it how to page. However, there is no explicit when-to-use guidance versus research_status or research_results, and no statement of prerequisites (e.g., that a job must already exist).

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

Deploy Server

Other Tools