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

Annotations already state idempotentHint=true, readOnlyHint=false, and destructiveHint=false, and the description is fully consistent with those. It adds substantial behavioral detail: it creates only when missing, updates in place only Otto's own lineage with stale rules, refuses by name any other installed policy, never downgrades a newer fence, and fails unless the read-back returns present under the written id.

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?

Although the description is long, each sentence adds distinct operational value: idempotency conditions, refusal behavior, downgrade protection, OPS restrictions, auth requirement, and output contract. It front-loads the core ensure-by-digest purpose before diving into constraints.

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 description is complete for an operation with no parameters: it specifies the auth header, when writes happen, when the tool refuses, the output fields, and the failure condition. Because an output schema exists, the return-value description is a bonus rather than a necessity.

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?

There are zero parameters, so there is nothing to explain in the input schema itself; the description explicitly confirms 'Arguments: {}'. It also explains why the listed schema is permissive: the strict schema is validated after the caller is authenticated, which prevents an agent from assuming the empty schema means no validation at all.

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 opens with a specific verb and resource: 'Idempotent ensure-by-digest of the ONE CDP project-scope policy that fences every delegated send, then a read-back.' This clearly distinguishes the ensure/mutate action from read-style siblings like otto_delegation_fence_status. The title reinforces the same purpose: installed and reads back as v-current.

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 gives strong usage context: it is an OPS action, never runs during a rolling deploy, never runs from the dApp, and runs at most one at a time project-wide. It does not explicitly say 'use otto_delegation_fence_status for inspection,' but it does distinguish the write path from the read path by mentioning the mint gate reads fence.present from otto_delegation_status.

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