legal_ediscovery

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

The description adds context beyond annotations by disclosing that calls route through the platform's domain-agent dispatcher under JWT, tenant, and company scope. It does not describe side effects, but the annotations already provide destructiveHint, idempotentHint, and openWorldHint signals. No contradiction with the annotations is present.

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 compact and front-loaded: the core action is stated in the first sentence, followed by routing scope and parameter definitions. Each sentence earns its place, and there is no filler or redundant restatement of the schema.

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?

The output schema and annotations cover return values and side-effect profiles, and the two parameters are defined in the description. However, the description lacks domain-level context about what eDiscovery actually does and provides no selection guidance relative to the many legal sibling tools. An agent can invoke it, but may not confidently know when it is the right 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 has no property descriptions (0% coverage), but the Args section compensates by defining both parameters: message as a "free-text objective" and inputs as an "Optional JSON string of structured inputs." This gives meaningful semantic guidance that the schema alone lacks, though the accepted structure of the inputs JSON remains open-ended.

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 states a clear action: "Run the legal domain agent action `ediscovery`." This gives a specific verb and resource, and the added routing/scoping sentence provides useful context. However, it does not explain what eDiscovery semantically accomplishes, and it does not explicitly differentiate itself from the many other legal_* sibling tools.

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?

No explicit when-to-use guidance or alternative tools are mentioned. The statement about routing through the domain-agent dispatcher describes mechanism, not selection criteria. Among dozens of legal domain siblings, an agent gets no clear basis for choosing this tool over legal_matter_intake, legal_contract_review, or dispatch_domain_agent.

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