Skip to main content
Glama

Nephia

by cc.nephia.api
OverviewDiscussionsAdmin

Replay a keyword's raw events or activity

get_keyword_events
Read-only

Read a keyword without a webhook receiver, across all its searches, newest first. kind=events replays the raw events since an ISO instant, each in the exact shape the webhook delivers: id, type, keywordId, source, the entity itself (listing, tweet, post and so on), previousPrice, analysis and occurredAt. That includes the types a mention does not carry, such as listing.price_changed and listing.delisted on vinted. For reading what people said, prefer get_keyword_results: a mention is the same catch, projected to a title and a body. kind=activity answers "is it polling, and did my webhook answer?". kind=runs lists the stored AI answer runs. Free — does not charge credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesKeyword id, from list_keywords. Another account's id is a 404, never a 403.
kindNo"events" (the default) replays what the keyword caught, each entry in the exact shape its webhook delivers; "activity" is the log of checks and webhook deliveries (poll.completed, poll.failed, webhook.delivered, webhook.failed) with eventsEmitted, creditsCharged, statusCode and message; "runs" is for a keyword that polls ai_answers and returns every stored answer run with its citations and brand mentions, including the runs that changed nothing, which is most of them and exactly what a trend is made of.
limitNoMax entries to return.
sinceNoOnly entries after this ISO 8601 instant.
engineNokind "runs" only: the runs of this engine.
sourceNoOnly this Source. Absent means every Source the keyword polls. Not with kind "runs".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

The readOnlyHint and openWorldHint already establish its non-mutating nature. The description adds useful behavioral context: events are replayed in webhook shape, activity logs checks and deliveries, runs includes no-op answer runs, and the operation is free and does not charge credits. There is no contradiction.

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 minimal, but every sentence adds value: it covers the primary use case, distinguishes the sibling tool, explains three modes, and notes the credit behavior. It is structured around kind values and remains efficient despite the complexity.

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?

With no output schema, the description must communicate return shapes, and it does: events lists the exact fields, activity lists the log entry fields, and runs are described as stored AI answer runs with citations and brand mentions. Ordering, mode behavior, and an alternative are also covered, making this complete for a six-parameter tool.

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%, so the schema already fully documents id, kind, limit, since, engine, and source. The description adds high-level meaning for the three kind values but does not meaningfully expand on parameter syntax or constraints beyond what the schema provides.

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 identifies a specific verb/resource pair: reading/replaying a keyword's events or activity. It explicitly distinguishes itself from get_keyword_results by explaining what an event includes beyond a mention amount, and the title reinforces the three kinds of data returned.

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

Usage Guidelines5/5

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

It states when to use this tool ('without a webhook receiver'), defines each kind's purpose, and explicitly points users to get_keyword_results when they want human-readable mentions. This is direct, actionable routing guidance.

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

All Nephia toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources