Skip to main content
Glama

query_calls

Retrieve and filter LLM call records by provider, model, time range, and latency for direct observability data access.

Instructions

Retrieve recent LLM call records captured by Argosvix. Filterable by provider / model / time range / tag. Defaults to the last 24 hours, 100 records.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNumber of records to return (1-500, default 100)
modelNoModel name to filter by (substring match). Omit for all models
beforeIdNoKeyset pagination cursor (id of the last row on the previous page). Must be used together with beforeTimestamp
providerNoProvider to filter by (openai / anthropic / gemini / mistral). Omit for all providers
latencyMaxNoUpper bound on response latency (ms, >= 0). Combine with latencyMin for a range
latencyMinNoLower bound on response latency (ms, >= 0). For outlier drill-down (e.g. "only calls over 2 seconds")
rangePresetNoTime range preset. Default 24h24h
beforeTimestampNoKeyset pagination cursor (timestamp of the last row on the previous page, ISO-8601). Must be used together with beforeId. Descending timestamp order only
Behavior4/5

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

With no annotations, the description must disclose behavior. It correctly labels the operation as 'Retrieve' (read-only) and mentions filtering capabilities and default parameters. However, it omits details like pagination behavior (though present in schema) and potential limits, but overall it provides sufficient transparency for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence but includes an undefined reference to 'tag' (not in input schema), which wastes space. It could be more structured (e.g., separating default behavior from filters). The front-loaded information is adequate.

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

Completeness3/5

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

Given 8 parameters and no output schema, the description is moderately complete. It covers the core purpose and defaults but does not mention pagination, ordering, or error conditions. The schema fills in many gaps, but the description could be more self-contained.

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 coverage is 100%, so the baseline is 3. The description adds no semantic value beyond what the schema already provides for each parameter. It mentions 'tag' (not in schema), which is slightly misleading, but the defaults are reiterated.

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 states the tool retrieves recent LLM call records. It specifies the resource ('call records captured by Argosvix'), the action ('Retrieve'), and key filtering dimensions (provider/model/time range/tag). It also distinguishes from sibling tools like aggregate_calls or export_calls by focusing on retrieval.

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?

The description implies usage for retrieving recent call records with filters, but it lacks explicit guidance on when to use this tool versus siblings (e.g., export_calls for bulk export, aggregate_calls for statistics). No when-not-to-use or alternative recommendations are provided.

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/argosvix/mcp-server'

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