Skip to main content
Glama

Nephia

by cc.nephia.api
OverviewDiscussionsAdmin

Run an AI pass over items

analyses_run

Read a set of items with one AI pass. Charges credits: 1 credit per 50 items for group, classify and summarise, and 1 credit per 25 for agent — the agent answers your own fields per item, which is heavier than a single verdict. The response's meta.credits_used is what was actually charged; a batch the provider could not answer is not billed. Estimate first with analyses_estimate if the cost matters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesgroup: cluster the items by an instruction. classify: sort them into buckets you define. agent: apply your instruction and schema to each item. summarise: answer one question about the set.
itemsNoThe items to read. Use exactly one of items or keywordId.
limitNo
sinceNoWith keywordId: ISO instant, defaults to 24h ago.
schemaNoRequired for kind=agent: 1-12 flat fields to answer per item. No nesting, no arrays. Every field may answer null — that is a real answer.
bucketsNoRequired for kind=classify.
questionNoRequired for kind=summarise.
keywordIdNoRead a keyword's own recent mentions instead of passing items. The id comes from list_keywords.
instructionNoRequired for kind=group and kind=agent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / items / description
      Previous value: -"The items to read. Use this or watchId, never both."New value: +"The items to read. Use exactly one of items or keywordId."
    • addedInput schema / properties / keywordId
      Added value: +{
+  "description": "Read a keyword's own recent mentions instead of passing items. The id comes from list_keywords.",
+  "format": "uuid",
+  "type": "string"
+}
    • changedInput schema / properties / since / description
      Previous value: -"With watchId: ISO instant, defaults to 24h ago."New value: +"With keywordId: ISO instant, defaults to 24h ago."
    • removedInput schema / properties / watchId
      Removed value: -{
-  "description": "Read a watch's own recent events instead of passing items.",
-  "format": "uuid",
-  "type": "string"
-}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses billing behavior: credits per item counts, actual charge reflected in meta.credits_used, and that unanswered batches are not billed. This is valuable operational context the annotations do not cover. No contradiction with annotations.

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?

Four sentences with no filler. The main purpose is front-loaded, cost and alternative are woven in, and the text is compact. It could be slightly tighter but is well-structured for quick consumption.

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?

Given 9 parameters and nested objects, the description covers cost, estimation, and the billing outcome. It mentions the response's meta.credits_used, giving a hint of the return shape, but does not fully describe the output structure. Since no output schema exists, a bit more detail on the response format would improve completeness, but it is sufficient for correct invocation.

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 89%, so the schema already documents most parameters. The description adds cost semantics per 'kind' (1 credit per 50 vs 25), which enriches that parameter's meaning. It does not add detail to items, limit, since, or schema parameters, but the schema covers them adequately. The added cost context justifies a slight upgrade from the baseline 3.

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 a clear verb and resource: 'Read a set of items with one AI pass.' It names the four kinds (group, classify, agent, summarise) and their distinct behaviors, making the tool's purpose unambiguous. It also references the estimation sibling, which helps differentiate when to use this versus analyses_estimate.

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 explicitly says to use analyses_estimate first if cost matters, providing a clear alternative. It explains the credit costs per kind, which informs when this tool is appropriate. However, it does not explicitly state when not to use this tool versus other exploration tools like explore, so it stops short of full exclusion 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