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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering safety and idempotency. The description adds critical behavioral guidance: 'pass async:true REQUIRED to avoid x402 timeout.' This is valuable beyond annotations and informs the agent of a required invocation pattern. It also describes outputs without contradicting 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 two concise sentences plus a critical async tip. It front-loads the core purpose, then covers inputs and outputs, and ends with an actionable warning. No unnecessary fluff.

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 has 5 parameters, nested objects, and an output schema, the description provides a solid overview: purpose, inputs, outputs, and the async requirement. It doesn't explain every parameter or the output schema structure, but the schema and output schema handle some of that, and the essential usage context is present. Minor gaps remain for include_network_flows and date_range format.

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 60%, and the description mentions key inputs ('incident identifiers, date ranges, or MITRE technique IDs') which adds some context. However, it does not detail the date_range structure or explain include_network_flows, and the async parameter is only mentioned in a passing note. The description adds moderate value but leaves gaps for parameters not covered by the schema.

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 states the tool's function: 'gather forensic evidence (logs, network flows, MITRE TTPs) from public breach reports and threat intelligence sources to support incident response post-mortems.' It uses a specific verb ('gather') and identifies the resource (forensic evidence) and context (incident response post-mortems), making it distinct from sibling tools like ai_act_incident_response.

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 provides clear context for when to use the tool: 'support incident response post-mortems.' It also hints at input flexibility ('incident identifiers, date ranges, or MITRE technique IDs'). However, it does not explicitly mention alternatives or when not to use it, which prevents a 5.

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