Opsphere — DevOps & SRE Intelligence

Sentry sessions by release (Release Health)

sentry_sessions_by_release

Read-only

Release adoption from Sentry Release Health: GET /organizations/{org}/sessions/ with field=sum(session) and groupBy=release. Do not use sentry_events_search or Discover for adoption %. statsPeriod=24h is whole-project mix; statsPeriod=1h reflects recent rollout. Alias concept: release adoption / sessions adopted.

Input Schema

Name	Required	Description
`topN`	No	Top releases by session count (default 10)
`period`	No	Alias of statsPeriod
`groupBy`	No	Default release
`orgSlug`	No	Organization slug; resolved from workspace when omitted
`projectId`	No	Numeric Sentry project id (sessions API project= param)
`context_id`	No	Optional explicit Connection Hub work context (ctx_*). Omit to use the conversation's active workspace; global Hub tools ignore it.
`environment`	No	Optional environment filter
`projectSlug`	No	Project slug; resolved with projectId via Sentry projects API
`statsPeriod`	No	Relative window (1h, 24h, 7d, 14d). Default 24h
`includeSeries`	No	Include hourly series buckets from Sentry
`highlightRelease`	No	Release version to echo in highlight; null if that release has zero sessions in the window

Output Schema

Name	Required	Description	Default
`ok`	Yes
`data`	Yes
`contractVersion`	Yes
`dataSchemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 26, 2026

addedOutput schema / properties / dataSchemaVersion

Added value: +{
+  "const": 2,
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "contractVersion",
-  "ok",
-  "data"
-]New value: +[
+  "contractVersion",
+  "dataSchemaVersion",
+  "ok",
+  "data"
+]

First observedOct 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld=false, and the description adds genuine context beyond them: the backing API shape, the meaning of different statsPeriod windows, and the semantics of highlightRelease returning null when a release has zero sessions. It does not discuss pagination or result shape, but the output schema covers that.

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?

Front-loads the purpose, then exclusions, then window semantics in three tight segments with no filler. Slightly dense (endpoint path plus alias line) but every clause is actionable.

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?

For an 11-param, no-required-args read tool with an output schema, the description supplies what structured fields cannot: routing exclusions and window-selection guidance. Defaults per parameter (topN=10, default release, default 24h) are mostly left to the schema rather than reinforced.

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 baseline is 3, but the description adds real meaning the schema does not: which window value to pick and what each implies, that groupBy is fixed to release, and that topN ranks releases by session count. That is value beyond the field docs.

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?

States a specific verb+resource ('Release adoption from Sentry Release Health') and pins it to the exact upstream call (GET /organizations/{org}/sessions/ with field=sum(session), groupBy=release). This is clearly separable from sentry_events_search, sentry_issues_* and the other Sentry siblings.

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?

Gives an explicit negative routing rule: 'Do not use sentry_events_search or Discover for adoption %', naming the alternatives to avoid. It also tells the agent how to choose between windows (statsPeriod=24h = whole-project mix vs 1h = recent rollout).

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

All Opsphere — DevOps & SRE Intelligence tools Inspect

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

Need Help?