analysis_exclusion_impact_preview

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

No annotations are provided, so the description must disclose behavioral traits itself. It explains return semantics ('unknown is an honest answer and never means no impact'), the guardrail consistency of 'would_block', and the existence of 'unevaluated_rules' to surface. It also notes that the delivery_records form reaches no platform API, effectively describing side-effect profile.

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 long but front-loaded with the core purpose in the first sentence. Each subsequent sentence earns its place by covering invocation modes, return semantics, and guardrail behavior. It is dense but not padded, though it could be slightly more concise without losing important nuance.

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?

Despite having no output schema, the description describes key return fields ('measured', 'partial', 'unknown', 'would_block', 'unevaluated_rules') and edge cases. It covers both platform-specific and generic usage, cumulative impact, and the distinction between inert and satisfied guardrails. For a complex tool with nested objects and six parameters, this is highly complete.

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 descriptions cover all six parameters (100% coverage), but the description adds meaning beyond the schema by explaining the two mutually exclusive parameter groups ('tool'+'arguments' vs 'excluded_entities'+'delivery_records') and clarifying the nuanced meaning of omitting 'standing_exclusions' versus passing an empty list. The mode distinction is not fully evident from the schema alone.

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 clear, specific purpose: 'Before applying a batch of exclusions / blocks / negative keywords, report how much of the account's OWN recent delivery... it removes'. The verb 'report' plus the resource (delivery impact) and the context (before applying exclusions) distinguish it from analytic sibling tools like analysis_anomalies_check or analysis_delivery_collapse_check.

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?

Usage context is explicit: 'Before applying a batch of exclusions...' and it contrasts the two invocation modes: with 'tool'+'arguments' for platform APIs, or with 'excluded_entities'+'delivery_records' for any other platform, noting the latter 'reaches no platform API'. It also advises to omit 'standing_exclusions' when unknown, providing clear when-to-use and when-not-to-use guidance.

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