assess_change_impact

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

Annotations already indicate readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral detail beyond that: 'Use only facts explicitly supplied by the user; never infer or default missing compliance facts' and 'Pass omissions through so the deterministic engine can return INSUFFICIENT_INPUT.' It also discloses that the tool returns an evidence-linked decision, complementing the structured annotations 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?

The description is four sentences, front-loaded with the core purpose and then covering usage, behavioral constraints, and output. Every sentence earns its place with no filler or redundant restatement of the tool name.

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?

Given the output schema exists, the description need not detail return values, and it covers usage scenarios, omission behavior, and decision/next-action output adequately. The main gap is no explicit 'not for' boundary or sample payload shape, but the description is still sufficient for an agent to select and invoke the tool correctly.

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?

With schema_description_coverage at 0% and a single opaque 'payload' object, the description must compensate, and it partially does. It explains that the payload contains only user-supplied facts, lists applicable change categories, and gives an example missing compliance fact (same_salary_option_still_met). It stops short of a full payload schema, but for a deliberately flexible payload this is substantive guidance.

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: 'Check whether a specific employee/company change affects UK Skilled Worker sponsor duties.' It then enumerates concrete change types (salary, role, work-location, TUPE, merger, etc.), which clearly distinguishes it from siblings like licensing_source_status and list_supported_change_events.

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 an explicit 'Use for' list covering the relevant change scenarios, and it also says to pass omissions through rather than infer defaults. It does not name alternative tools for when-not/exclusion scenarios, so it has clear context but no explicit sibling routing.

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