Skip to main content
Glama
consetto

calmcp

by consetto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Query SAP Cloud ALM analytics

calm_analytics
Read-only

Query SAP Cloud ALM analytics providers for tenant-wide totals and grouped breakdowns across defects, tasks, tests, features, and projects using filters; returns counts, not sorted records.

Instructions

Query an SAP Cloud ALM analytics provider (Defects, Tasks, Tests, Features, Projects, Metrics, ...). Supports $filter, and aggregates: it is the tool for tenant-wide totals and breakdowns. It does NOT sort — $orderby is ignored, so sort the records yourself. Every provider spans the whole tenant, so this is how you count without naming a project: count_only=true for a total, group_by="status" for a breakdown (Defects: "defectStatus"). Tasks covers user stories, defects and requirements; filter them by type CODE, e.g. filter="typeID eq 'CALMUS'" (the type text is silently ignored).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNoOData $top — maximum number of records
skipNoOData $skip — records to skip
countNoReturn the total as "@count" ALONGSIDE the records (OData resources and analytics only). For a total without the records, use count_only instead
filterNoOData $filter, e.g. "status eq 'CIPDFCTOPEN'"
periodNoAnalytics time window, sent inside $filter. Format <L|C><n><H|D|W|M|Y>, e.g. "L1D" (last day) or "C1M" (current month). Counting defaults to "C1D" so each record is counted once
selectNoOData $select — comma-separated field list
group_byNoComma-separated field name(s) to break the count down by, e.g. "status" or "projectName,status". Returns {total, groups:[{value,count}]} instead of records. Also the quickest way to discover which values a field actually takes
providerYesAnalytics provider (e.g. Defects, Tasks, Tests). Every provider spans the whole tenant, so this is the only way to count without naming a project. It aggregates but does not sort: the service ignores $orderby, so never present its output as sorted
count_onlyNoReturn ONLY the total number of matching records, no records at all. Use this for every "how many ...?" question — the answer is a few hundred bytes instead of hundreds of KB. Works for every resource and provider
resolutionNoAnalytics bucket size, sent inside $filter: D, W, M or Y. A record appears once per bucket, so a wide window with a small bucket multiplies the count. Counting defaults to "D"
group_limitNoMaximum groups returned by group_by (default 50); the rest fold into otherCount

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.9.2
    • addedInput schema / properties / group_limit / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / skip / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / top / maximum
      Added value: +9007199254740991
  2. Changed8 schema fields changedv0.9.0
    • addedInput schema / properties / count
      Added value: +{
+  "description": "Return the total as \"@count\" ALONGSIDE the records (OData resources and analytics only). For a total without the records, use count_only instead",
+  "type": "boolean"
+}
    • addedInput schema / properties / count_only
      Added value: +{
+  "description": "Return ONLY the total number of matching records, no records at all. Use this for every \"how many ...?\" question — the answer is a few hundred bytes instead of hundreds of KB. Works for every resource and provider",
+  "type": "boolean"
+}
    • addedInput schema / properties / group_by
      Added value: +{
+  "description": "Comma-separated field name(s) to break the count down by, e.g. \"status\" or \"projectName,status\". Returns {total, groups:[{value,count}]} instead of records. Also the quickest way to discover which values a field actually takes",
+  "type": "string"
+}
    • addedInput schema / properties / group_limit
      Added value: +{
+  "description": "Maximum groups returned by group_by (default 50); the rest fold into otherCount",
+  "exclusiveMinimum": 0,
+  "type": "integer"
+}
    • removedInput schema / properties / orderby
      Removed value: -{
-  "description": "OData $orderby, e.g. \"priority desc\" (OData resources / analytics only)",
-  "type": "string"
-}
    • addedInput schema / properties / period
      Added value: +{
+  "description": "Analytics time window, sent inside $filter. Format <L|C><n><H|D|W|M|Y>, e.g. \"L1D\" (last day) or \"C1M\" (current month). Counting defaults to \"C1D\" so each record is counted once",
+  "type": "string"
+}
    • changedInput schema / properties / provider / description
      Previous value: -"Analytics provider (e.g. Defects, Tasks, Tests). Supports $orderby."New value: +"Analytics provider (e.g. Defects, Tasks, Tests). Every provider spans the whole tenant, so this is the only way to count without naming a project. It aggregates but does not sort: the service ignores $orderby, so never present its output as sorted"
    • addedInput schema / properties / resolution
      Added value: +{
+  "description": "Analytics bucket size, sent inside $filter: D, W, M or Y. A record appears once per bucket, so a wide window with a small bucket multiplies the count. Counting defaults to \"D\"",
+  "type": "string"
+}
  3. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing non-obvious behaviors: no sorting, tenant-wide scope, silently ignored type text, default counting windows (C1D/D). These are exactly the traps an agent would otherwise fall into.

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?

Dense but front-loaded: capability, then the exclusion, then the counting/grouping recipes. No filler sentences; each clause carries a usable fact.

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?

With 11 parameters, no output schema, and an analytics service full of sharp edges, the description supplies the operational contract (counting defaults, bucket multiplication, group folding) needed to call it correctly. Nothing essential is missing.

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; the description nonetheless adds cross-parameter meaning (count vs count_only distinction, group_by as a value-discovery tool, filter syntax with typeID code) that the schema only partially implies.

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 (query an SAP Cloud ALM analytics provider) and enumerates the provider domain. It clearly positions itself against siblings by framing itself as the tenant-wide totals/breakdown tool, distinct from calm_get/calm_list/calm_resources.

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?

Explicit when/when-not guidance: count_only=true for total, group_by for breakdown, and an explicit negative ($orderby is ignored, sort yourself). It also routes the type-filtering case with a concrete example, so an agent knows exactly which knob to turn.

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

Deploy Server

Other Tools