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

Annotations already carry readOnly, idempotent and non-destructive hints, but the description adds meaningful behavioral context beyond them: the API-key scope requirement, the disabled-by-default gate, and an explicit list of authorities it does NOT have (cash probe, signer, custody, spending, release, refund, scheduler). This clarifies the safe blast radius well.

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?

Front-loaded with the action and the key auth gate, and no sentence is pure filler. But 'Partial native history remains unknown with zero safe/advisory surplus' is near-opaque jargon that consumes space without conveying actionable meaning to an agent.

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?

No output schema exists, so the description must frame the operation, which it does via scope, gating, and explicit authority exclusions for a zero-parameter read. It is largely complete for a read tool, with only the return-shape and the ambiguous 'projection' semantics left 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?

The tool takes zero parameters (schema coverage 100%, additionalProperties false), so there is no parameter surface to document; baseline 4 applies. The description reinforces the zero-selector design with 'No caller owner/role selectors.'

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 clear verb (Read) and resource (obligation projection for the server-delegated reader), and the title reinforces 'Read delegated Operator obligations'. The qualifiers 'conservative' and 'projection' are opaque jargon, but the core action is discernible and it is distinguishable from history/profile siblings.

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?

It specifies a real precondition -- requires server-delegated reader identity and explicit operator:read API-key scope, and is disabled without protected reader/role configuration. However, it never names alternatives or tells the agent when to prefer a sibling like history_read or keryx_operator_status, leaving selection to inference.

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