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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false. The description goes well beyond that, disclosing the idempotency-key retry contract, the canonicality/trust-the-backend behavior in lieu of a state-recovery call, and the confirmation boundary. It is boilerplate-heavy but genuinely adds behavioral context for a mutation tool.

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 opening two sentences are well front-loaded and earn their place. The back half (Canonicality, Idempotency, Confirmation boundary) is generic boilerplate that repeats cross-tool policy text rather than tool-specific detail, diluting an otherwise tight description.

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?

With no output schema, the description usefully tells the agent to trust actual_tool_output and context_engineering rather than issuing a recovery call, which covers the return-value gap. Given 12 parameters and 10 required fields with no schema descriptions, it is close to complete but still leaves several input fields unexplained.

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 description coverage is 0% across 12 parameters, so the description must carry the load. It does explain priorInventions and priorAgreements semantics (record explicitly, even when None), the workState/relationship intent, the appointmentCaseId link, and the idempotency key. However, several parameters (email, address, companyOfficerPersonId) get no guidance, so it only partially compensates for the coverage gap.

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?

States a specific verb (Prepare) and a specific legal instrument (bilateral confidential-information and invention-assignment agreement), scopes it to a named employee/consultant/director in DE or GA, and explicitly distinguishes it from siblings that appoint or issue equity. An agent can separate this from propose_restricted_stock_issuance or record_company_director_appointment without reading either schema.

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?

Gives a clear when-to-use context (preparing an IP assignment for a named person, optionally linked to a completed appointment case) and a prerequisite (authenticated active company access). It stops short of naming any alternative tool or an explicit when-not-to-use case, so it falls just below the top band.

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