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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description adds substantially more: the result is a private encrypted draft, the operation is idempotent, no provider call occurs, and granted-path preparation is gated by server-side checks plus an active pilot session. It does not explain encryption scope or idempotency-conflict behavior, so not a 5.

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 tight sentences, front-loaded with the action and artifact, then eligibility, then the negative boundary. Every sentence carries information; density comes from domain jargon rather than filler.

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?

An output schema exists, so return values need not be described. The description covers eligibility, gating, and the crucial fact that no provider call happens. Remaining gap is the lifecycle linkage — what the returned intent is consumed by (presumably execute_provider_invocation) and how long the draft stays valid.

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 50%: 'input' and 'idempotencyKey' are documented in the schema, while projectId and operationId are bare strings. The description indirectly constrains operationId ('owned approved operation or a granted read-only operation') and implies idempotency via 'idempotent', but adds nothing about projectId or how idempotencyKey interacts with replay. Partial compensation for the coverage gap, so a 3.

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 concrete verb and artifact ('create an encrypted, idempotent invocation intent') scoped to two eligible operation types (owned-approved or granted read-only). The closing clause 'This does not call the provider' cleanly separates it from the sibling execute_provider_invocation. Minor deduction because 'owned approved operation' and 'granted read-only operation' are internal jargon that an agent may not fully resolve.

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?

Preconditions are stated (approved operation, granted read-only, independent server gates, active consumer pilot session), which is real usage context. However, it never explicitly says to use execute_provider_invocation to actually perform the call, nor when to prefer this over get_provider_invocation or request_provider_access. The alternative is only implied via negation.

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