Audit Feature Manifest

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

Annotations already mark this as read-only, idempotent, and non-destructive. The description adds valuable behavioral detail: it flags banned actuals sources, features predating tape start, unknown features fail closed to tier C, and an optional coverage check against MIN_COVERAGE=0.90. No contradiction with 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?

Two tight sentences with no filler. The core action is front-loaded, the manifest structure is given compactly, and the optional coverage check is described in one clause. Every sentence earns its place.

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 and annotations cover the safety profile, the description is highly complete: it explains what gets flagged, the fail-closed behavior, and the optional coverage mode. Minor gaps such as what exactly 'tier C' means or how output is structured are covered by the schema or context.

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 description coverage is 100%, but the description enriches parameter meaning by explaining the manifest shape ({name, source, value_ts, as_of}) and the purpose of selected_symbols/snapshot_universe in the coverage check with the absolute MIN_COVERAGE=0.90 threshold.

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: 'Audit a feature manifest for lookahead leakage and provenance violations.' It then details the exact checks performed, which clearly distinguishes this tool from sibling tools like cost_check, validate_order, and promotion_verdict.

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 implies usage context: use this tool when you need to audit a feature manifest for lookahead/provenance issues. However, it never explicitly states when not to use it or names alternative tools that might be more appropriate for related validation tasks.

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