rtcStats

get_session

Returns full session payload for one stored session (summary, observations, scores, etc.). Arguments: rtcstatsId (UUID). In data.observations[], each observation has type, severity, category, tags, firstSeenAt and a source object whose properties depend on the category: source.pid (peer connection id), source.sid (stream/datachannel report id), source.cpid (candidate-pair id), source.did (device entry id), source.rid (device row index), source.timestamp (device entry time), source.ssrcId (number, stream SSRC), source.labelId (device name). The top-level label is DEPRECATED and removed in the next schema version (overloaded legacy id; read source.ssrcId / source.sid / source.labelId instead). The full catalog of observation types (with possible severities and tags) is available from GET /v1.0/observations. Requires Authorization: Bearer on the MCP HTTP request.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rtcstatsId`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`embedUrl`	No
`rtcstatsId`	Yes
`rtcstatsUrl`	Yes
`processorVersion`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden. It discloses the required Authorization header, the deprecation of the top-level label, and the conditional structure of source properties based on category. It also references an external catalog for observation types, adding meaningful behavioral context.

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?

The description is information-dense and well-structured: it starts with purpose, then parameter, then details of observations, deprecation, catalog reference, and auth. Every sentence adds value, and the length is appropriate for a tool with a complex response payload.

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?

Given the tool's complexity (nested observations with category-dependent source objects) and the lack of annotations, the description is thorough. It covers auth, deprecation, data structure, and external references, providing sufficient context for an agent to use the tool correctly.

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 only parameter rtcstatsId is described as a UUID, which adds semantic meaning beyond the schema's generic 'string' type. However, it does not explain how to obtain or validate the ID, and with 0% schema coverage, the description only partially compensates.

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 returns a full session payload for one stored session, using a specific verb ('Returns') and resource ('full session payload'). It distinguishes from siblings by emphasizing 'one stored session' versus list_sessions (listing) and get_quota (quota).

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 clear context: use this tool when you have a specific rtcstatsId and need full session details. It does not explicitly mention alternatives or exclusions, but the context is sufficient to infer when to use it over list_sessions.

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

All rtcStats tools Inspect

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

A4.4/5.0

Disambiguation5/5

Each tool serves a clearly distinct purpose: get_quota handles account information, get_session retrieves a single session by ID, and list_sessions provides filtered search. No overlap in functionality or ambiguity in selection.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_quota, get_session, list_sessions), making the API predictable and easy to navigate.

Tool Count4/5

With just 3 tools, the set is minimal but coherent for a read-only RTC stats server. The count feels slightly thin but each tool covers a distinct need without redundancy.

Completeness4/5

The core workflows (check quota, list sessions, fetch session details) are covered. A notable gap is the lack of a tool to access the observation catalog mentioned in get_session, which would be useful for interpreting observation types.

Resources

Need Help?