Investigate Problem

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, and the description adds meaningful behavioral context on top: it reports the problem's start time, prior duration, co-failing hosts/services, and preceding configuration changes. It also discloses a fallback behavior for a hostname that matches no host, saying the answer includes tools that can find the right one. There is no contradiction with the annotations.

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?

The description is three sentences, front-loaded with the core purpose and followed by concrete invocation examples. Every sentence earns its place: the first defines the tool's scope, the second clarifies the problem-selection behavior, and the third gives reusable use cases. There is no filler or repetition of schema fields.

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?

Given the 100% input-schema coverage, an output schema, and strong annotations, the description is sufficient for invocation: it explains what the tool looks at, how it chooses the relevant problem, and when to reach for it. A fully complete definition might explicitly mention response shape or more precise failure-query scenarios, but the output schema covers the return contract.

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?

The input schema has 100% parameter coverage, so the schema already documents 'hostname', 'servicename', 'days', and 'around_minutes' clearly. The description's main added value is the hostname note about no estate-wide form, which is also partially restated in the schema. This matches the baseline for a fully schema-covered tool.

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 clearly explains what the tool does: it reconstructs what happened around a problem, including first occurrence, prior occurrences, other failing hosts/services, and relevant configuration changes. It does not use a single explicit verb+resource construction inventor but the concrete list of behaviors and two example questions make the purpose specific. It is distinguishable from the sibling list by its problem-history focus, though it does not name a sibling alternative.

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?

The description gives explicit example questions for when to use the tool: 'why did web01 go down' or 'has Backup on db01 failed before'. It also states that it works on the current problem or the last one if the object is healthy nowainer, which is useful context. It does not give when-not-to-use conditions or name alternatives, so it stops short of a 5.

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