osint_investigate_email_start

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

Annotations include readOnlyHint=false (indicating mutating/start) and idempotentHint=false, but description clarifies it starts an async process and returns an investigationId immediately, which is beyond annotations. It also discloses the restricted access (owner/enterprise tier) and the restriction on people-centric OSINT to prevent misuse. This adds valuable behavioral context not present in 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?

Three sentences, no redundancy. Front-loads the action and purpose, then adds restrictions and next steps. Every sentence earns its place.

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?

Contextual complexity is moderate: async operation, restriction, and follow-up tools are mentioned. No output schema, but description explicitly tells how to get results via other tools, so return value is covered. Minor gap: doesn't specify what happens if query is invalid or requires additional auth beyond tier, but overall sufficient.

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 has only one parameter 'query' with min/max length but no description; coverage is 0%, so description must compensate. Description implies 'query' is the email address, but doesn't explicitly state format or validation. However, given only one param, it's fairly inferable. Baseline for 0 params would be 4, but single param with implied type is okay; still, explicit mention would improve.

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 states specific verb and resource: 'Start an async OSINT investigation for an email address' with explicit scope ('breach exposure, account correlation'). It distinguishes from siblings by noting the email-specific variant and the async nature, setting it apart from domain, infrastructure, supply chain, and username variants.

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?

Clear context: mentions it is restricted to owner/enterprise tier, which is a usage condition. It also directs to poll with osint_investigation_status and retrieve with osint_investigation_report, providing next steps. However, it doesn't explicitly state when NOT to use this tool (e.g., for non-email queries) or alternatives beyond the sibling tools, though the sibling context implies alternatives.

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