Get Control Delta

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

With no annotations, the description carries the full load and does substantial work: it declares read-only/no-side-effects, enumerates the meaning of each 'status' value, explains that sufficiency is judged against a declaration once made, and states explicitly that dismissing a finding is a person's act 'made in the app, never a program's.' It omits permission/auth requirements and any rate or cost characteristics, but the side-effect and human-gate disclosures are unusually thorough.

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 purpose is front-loaded, but the bulk of the text is an exhaustive walkthrough of the return payload even though an output schema already exists. The single most operationally important instruction (relay findings, never dismiss programmatically) is buried at the very end and the prose is dense with dangling references ('...' in the field list).

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?

Because an output schema exists, the long return-value narration is largely redundant, and the description leaves gaps in usage routing and parameter meaning. It is complete on the conceptual behavior of the delta (status, cross_check, sufficiency gating), which is the genuinely non-schema knowledge, so it is adequate but not fully sufficient for a tool with many adjacent siblings.

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 67% and the description adds nothing about any of the three required parameters — no meaning, format, or constraints for model_id, control_id, or the undocumented server_version. All parameter meaning rests on the schema, and one parameter has none.

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 and resource and even defines the jargon: 'Read the delta of a control: the edits to the behavioural model that the control's own text commits to.' The 'Read-only; no side effects' clause implicitly separates it from the write-side siblings submit_control_delta and declare_control_delta, though it never names them.

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 never says when to call this tool versus submit_control_delta, declare_control_delta, or request_delta_second_reading. The only imperative, 'RELAY OPEN FINDINGS TO THE PERSON,' is an in-app human action, not a condition for invoking the tool. Usage is left entirely to inference.

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