Analyze an open incident and recommend the next action: run a specific runbook, escalate to a human, resolve, or wait. Returns the recommendation (with rationale and confidence) and the candidate runbooks. This is analysis ONLY — it does not change anything. Call this to decide what to do about an incident; then confirm with the user before calling run_runbook.
| Name | Required | Description | Default |
|---|---|---|---|
| incidentId | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's 'does not change anything' is reinforcing rather than new — but it earns credit for disclosing the return payload shape (recommendation with rationale and confidence, plus candidate runbooks) and the human-in-the-loop gate before run_runbook. It stops short of noting whether only open incidents are eligible or what happens on a closed/already-resolved incident.
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 tight, front-loaded sentences: purpose, return value, then the safety constraint and follow-up. Minor redundancy between 'analysis ONLY' and 'it does not change anything', which restates the same point twice.
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?
No output schema exists, yet the description covers the return contract (recommendation, rationale, confidence, candidate runbooks) and the required next-step workflow. For a single-parameter read-only analysis tool, nothing essential is missing.
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?
One parameter with 0% schema description coverage, so the description would need to carry semantics for incidentId. It only indirectly implies the constraint via 'open incident' — there is no statement of the ID format, where to obtain it (e.g. list_incidents), or what happens for a non-open incident.
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?
States a specific verb and resource ('Analyze an open incident') and enumerates the outcome space (runbook / escalate / resolve / wait), which cleanly separates it from mutating siblings like resolve_incident and run_runbook. The read-only framing ('analysis ONLY') further disambiguates it from the action tools.
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?
Explicitly says when to call it ('to decide what to do about an incident') and prescribes the follow-up sequence: confirm with the user, then call run_runbook. It also names the alternatives it competes with (escalate, resolve, wait) rather than leaving routing to inference.
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.
