Finds deploys and feature-flag flips in a chosen time window for a service and its dependencies, helping diagnose production incidents by linking changes to root cause.
Deploys and feature-flag flips in the time window, scoped through the graph to service
(plus everything it depends on, and flags that affect those services).
| Name | Required | Description | Default |
|---|---|---|---|
| minutes | No | ||
| service | No | ||
| include_dependencies | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral context: results are scoped through the dependency graph, not just the named service, and feature flags affecting those services are included. It omits defaults (120 minutes), pagination, and return shape, but with annotations present this is adequate.
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?
A single dense sentence with the returned resource front-loaded and the scoping constraint trailing. No filler, no repetition of the tool name. Slightly heavy on nested parentheticals but earns its place.
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?
With no output schema the description must convey what comes back, and it does name the returned entities. But for an investigation tool it lacks usage framing, default behavior for the null service case, and any note on ordering or volume limits, leaving material gaps.
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?
Schema coverage is 0%, so the description carries the param burden. It implicitly maps all three parameters - 'time window' for minutes, 'scoped to `service`' for service, 'plus everything it depends on' for include_dependencies - which is better than nothing. However it gives no default values, units, or format, and never explains what happens when service is null.
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 the resource precisely - deploys and feature-flag flips - and states the scoping semantics (graph traversal to `service` plus its dependencies). An agent can tell this apart from siblings like get_blast_radius or query_graph without opening the schema. It stops short of a clean verb (e.g. 'list'), but the content is unambiguous.
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?
There is no statement of when to use this tool versus alternatives such as rank_suspects, get_blast_radius, or explain_incident. The incident-investigation context is only implied by the sibling set. No prerequisites, no exclusions, no routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.