List this account's active anomaly suppressions — signatures (a provider+service pair, or a tag_key+tag_value) a human has marked as expected, so the detector stops surfacing them. Each has an expires_at (null = indefinite). Mirrors GET /api/accounts/:accountId/anomaly-suppressions. Creating/deleting a suppression is not available over MCP.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, and the description aligns with those. It adds useful behavioral context beyond annotations: only active suppressions are returned, each item carries an expires_at field (null meaning indefinite), and the tool mirrors a REST endpoint while MCP write operations are unavailable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each earning its place: definition of a suppression, the key expires_at field, and the MCP limitation. Information is front-loaded and no filler exists.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, read-only list tool with no output schema, the description is complete: it defines the items, the filtering to active ones, the expires_at semantics, and the endpoint equivalent. An agent can correctly invoke and interpret this tool without further clarification.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0 parameters, there are no parameter semantics to document. The baseline of 4 applies; the description correctly explains what the result represents so the agent understands the tool's purpose despite having no inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb ('List'), resource ('anomaly suppressions'), and scope ('this account's active'). It clearly distinguishes this from sibling tools like list_anomalies by explaining these are human-marked-as-expected signatures that suppress detector findings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context: this lists suppressions that are currently active and explains what a suppression is. It also states that creating or deleting suppressions is not available over MCP, which sets an explicit boundary, though it does not name alternative tools because none directly competes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are organized by resource (budgets, alerts, anomalies, dashboards, cost tags, recommendations), so most are clearly separable. The cost-tag cluster and the dimension/facet listers are the places where an agent could misselect by name, though descriptions resolve the ambiguity.
All tools use snake_case verb_noun names with a clear convention: get_ fetches specific items, list_ enumerates collections, and query_ runs time-bucketed or analytical queries. The pattern holds across all 29 tools with no camelCase or mixed verb styles.
29 tools is well past the typical 3–15 sweet spot and even past the 16–25 heavy band, so the surface feels sprawling despite having few duplicates. Each tool maps to a distinct endpoint, but the sheer number makes it a heavy set for an agent to select from.
The read-side is strong: costs, usage, tags, budgets, alerts, anomalies, dashboards, recommendations, and data health are all queryable. However, the surface is almost entirely read-only, and descriptions reference absent tools like create_budget, create_alert_subscription, create_dashboard, set_dashboard_widgets, and delete_dashboard, creating dead ends. That is a significant gap for a cost-management platform.