scf_set_scope_override

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

Annotations already provide readOnlyHint=false and destructiveHint=false, so the description doesn't need to restate safety. It adds value by disclosing the write nature ('write — editor+'), the effect on override (pin or clear), and the important side effect of 'inherit': 'discards the recorded rationale (it stays in the audit trail)'. This goes beyond annotations, making the agent aware of data loss on rationale. However, it doesn't detail permissions beyond 'editor+' or response format, but that is acceptable given annotations.

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 description is only three sentences, front-loads the core purpose, and every word earns its place. It states the primary function, explains actions concisely, and adds the crucial constraint 'Scope only, not status' efficiently. No redundancy or 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?

For a single-control mutation tool with complete schema documentation, the description provides sufficient context. It covers the control's scope override mechanism, the three actions, and the side effect of inheriting. It doesn't mention return values (no output schema) or error conditions, but those are not critical for making the call. The description is complete enough for an agent to execute correctly, and the small gaps are acceptable given schema richness.

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 100%, but the description enhances parameter understanding. It explains the action enum's semantics clearly (include/exclude pin, inherit clears) and notes that 'inherit' also discards rationale, which is not in the schema. It also clarifies the scope of the tool ('Scope only, not status') which helps interpret scf_id and action. Although it doesn't restate each parameter, it adds value on top of the schema.

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 states a specific verb ('Force'), a clear resource ('one control'), and the precise effect (in or out of scope, pin/include/exclude/inherit). It distinguishes itself from siblings by clarifying it operates on a single control's override, not batch operations like scf_batch_update_controls or scf_bulk_unscope_framework. The parenthetical '(write — editor+)' and 'Scope only, not status' further delineate its exact place in the toolkit.

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 explicitly explains the three action values ('include'/'exclude' pin it; 'inherit' clears the override) and notes the scope-only limitation ('Scope only, not status'). It does not directly name a sibling to use instead, but the contrast with batch tools is implicit through 'one control' and 'single control'. The context of scf_set_scope_override vs. scf_batch_update_controls and scf_bulk_unscope_framework is clear enough for an agent to select it correctly.

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