Built-in diagnostics

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

Annotations already declare readOnly, non-destructive, idempotent behavior, so the description only needs to add behavioral context. It does add meaningful specifics: the two-step list-then-run pattern and the fact that it surfaces managed platform diagnostics not available through direct queries. No contradiction with annotations exists.

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 tightly structured: first sentence states the action and scope, second lists the valuable diagnostic categories, third gives the call pattern. Every sentence earns its place with no redundancy or filler.

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 read-only tool with no output schema, the description covers what the tool does, which resources it targets, why an agent would choose it, and how to sequence calls. It does not describe result shape or pagination, but given the rich annotations and clear workflow, the agent has enough to invoke it correctly.

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 description coverage is 100%, so all three parameters are already documented. The description reinforces the detector parameter's omit-to-list behavior and gives workflow guidance, but it does not add substantive semantic detail beyond the schema. Baseline 3 is appropriate.

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 opens with a specific verb-plus-resource ('Runs Azure's built-in 'Diagnose and solve problems' detectors') and names the exact resource types (App Service, Function apps, Container Apps). It further lists concrete diagnostic outcomes (crashes, restarts, HTTP 5xx, CPU/memory pressure, SNAT exhaustion), making the tool's scope unmistakable and distinguishing it from generic log or metrics siblings.

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 a clear workflow: call without a detector to list detectors, then call again with a detector id. It also signals the appropriate context ('platform data you cannot query yourself'), which implies when to prefer this over raw log/metrics tools, though it does not explicitly name alternatives or state when not to use it.

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