run_discovery_scan

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, and the "[CMDB Write]" tag merely echoes the write hint. The phrase "trigger a Discovery scan" does convey a real external action, but the description omits that the scan is likely asynchronous, whether repeat calls launch duplicate scans, and what comes back.

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 compact sentence with the write classification front-loaded and no filler. The trailing "for network/infrastructure" adds little, but nothing is wasted overall.

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 non-idempotent, open-world write with no output schema, the description should say whether a run is started and a run id returned, and whether results are retrievable via list_discovery_runs. The safety profile is covered by annotations, but the post-invocation story 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?

Schema coverage is 100%, so both schedule_id (required) and optional mid_server are fully documented in the schema, and the description adds no syntax, format, or MID-pinning semantics beyond it. A baseline 3 is appropriate when the schema carries the load.

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?

"[CMDB Write] Trigger a ServiceNow Discovery scan for network/infrastructure" gives a specific verb (trigger) and resource (Discovery scan), and the write tag separates it from read-only siblings like list_discovery_runs and list_discovery_schedules. It stops short of explicitly naming the relevant sibling, but the action 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?

The description never states when to use this versus list_discovery_schedules (inspect first), list_discovery_runs (check results), or trigger_scheduled_job. No prerequisites, no note on when a MID server pin is warranted, and no exclusions.

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