Opsphere — DevOps & SRE Intelligence

Recent errors (Datadog logs)

dd_errors_recent

Read-only

Deduplicated error sample from Datadog logs (not full window coverage). pageTotal is window volume; sample comes from up to maxLogEvents fetched logs. Use dd_errors_by_service first, then call with service and hours<=6. Default query: status:error OR 5xx.

Input Schema

Name	Required	Description
`hours`	No
`limit`	No	Max deduplicated error signatures in sample
`query`	No	Override default error query
`service`	No	Plain service name only (e.g. "edge", "storefront"). Do NOT pass attribute filters like "env:prd" — include those in the query parameter instead.
`context_id`	No	Optional explicit Connection Hub work context (ctx_*). Omit to use the conversation's active workspace; global Hub tools ignore it.
`maxLogEvents`	No	Max raw log events to fetch before deduplication

Output Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 26, 2026

changedOutput schema / properties / data / additionalProperties
```
Previous value: -trueNew value: +false
```

changedOutput schema / properties / data / properties / sample / items / additionalProperties

Previous value: -trueNew value: +{
+  "type": [
+    "string",
+    "number",
+    "boolean",
+    "null"
+  ]
+}

removedOutput schema / properties / data / properties / sample / items / properties
```
Removed value: -{}
```

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

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnly/destructive annotations by disclosing the sampling model: pageTotal is window volume while the sample is drawn from up to maxLogEvents fetched logs, and coverage is explicitly not full-window. That is exactly the caveat an agent needs to avoid over-interpreting counts from this tool.

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?

Three dense, front-loaded sentences with no filler; sampling caveat first, then routing, then default query. The 'pageTotal' sentence is slightly terse and assumes the output schema is available to decode it, but nothing is wasted.

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?

For a 6-parameter, zero-required, read-only tool with an output schema, the description covers the essential gaps: sampling limitations, sequencing relative to the sibling, and the default query. Return-value shape is left to the output schema, which is appropriate.

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 already 83%, so the baseline is 3; the description adds real value by tying maxLogEvents to sample size and stating the default error query that applies when query is omitted. The hours parameter's semantics (window for pageTotal) are only implied rather than stated.

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 and resource ('Deduplicated error sample from Datadog logs') with an explicit scope qualifier ('not full window coverage'). It names the sibling it complements ('Use dd_errors_by_service first'), so an agent can distinguish it without opening the schema.

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?

Gives a clear workflow ('Use dd_errors_by_service first, then call with service and hours<=6') including a concrete constraint on the hours parameter. It lacks an explicit 'do not use for X' exclusion (e.g. broad triage or long windows), so it stops just short of the top score.

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?