analyze_report

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

Discloses significant behavioral details beyond sparse annotations: live HTTP validation requests contacting external services, authentication requirements, polling behavior, and timeout return. No contradiction with annotations (readOnlyHint=false is consistent with side effects).

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?

Single paragraph with multiple well-structured sentences; information is front-loaded with primary action. Packed but efficient, though could be slightly improved with bullet points for readability.

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 tool's complexity (async, side effects, authentication, multiple parameters), the description covers all necessary aspects for correct usage, including progression states, return behavior, and prerequisites. Output schema exists, so return format documentation is not required.

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?

All four parameters are covered in schema (100% coverage), but description adds actionable context: conditional use of report_file, blocking semantics of wait_minutes, and source of report_uuid. This adds value beyond bare schema descriptions.

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?

Description clearly states the tool submits or advances async AI credential validation for previously uploaded scan reports, with specific verb ('submit or advance'), resource ('async AI credential validation'), and scope. It distinguishes from sibling scan tools that collect data.

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?

Provides clear usage steps: call once to queue, poll until complete, pass report_file when status is 'waiting_client', use wait_minutes to block. Context is clear but lacks explicit exclusions or direct comparison to alternatives like get_scan_status.

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