get_exploit_analysis

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds value by detailing the rich output (deception indicators, backdoor-review verdict, operator-risk notes) and confirming it's a safe read operation.

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 a single paragraph that efficiently conveys purpose, output fields, usage guidance, and an example. It is front-loaded with the main purpose and remains compact without unnecessary words.

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 no output schema, the description enumerates the return fields comprehensively, including classification, attack type, complexity, etc. It also explains the typical use case and provides an example, making it complete for a single-parameter tool.

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 covers 100% of parameters with a description for exploit_id. The description adds clarity by noting it's not the EDB number and providing an example (exploit_id=61514), which helps the agent understand the exact value to use.

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 explicitly states the tool gets the full AI analysis for a single exploit by platform ID, listing all returned fields. It distinguishes from siblings like get_exploit_code (code retrieval) and search_exploits (listing) by specifying the unique output and use case.

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 clearly advises using this tool to check if an exploit is safe before reviewing its code, with an example. While it doesn't explicitly state when not to use it, the context implies it's for a single exploit by ID, and the alternative sibling tools cover other needs.

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