gap_scan

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

Annotations already mark it as read-only (readOnlyHint=true) and non-destructive. The description adds that it 'scans the local Decision Graph' and enumerates the types of issues detected. It also clarifies the behavior of actionable:false as a no-op, which is not in 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 concise sentences: first defines purpose, second gives usage advice. Every phrase adds value; no redundancy or extra detail.

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?

The description gives enough context for an agent to understand the tool's role and behavior. However, without an output schema, it does not describe return format or detailed output for the non-digest mode, which would improve completeness.

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%, so the description's parameter details are supplementary. It adds context by describing digest_only as 'hands-off mode' and clarifying that reference_systems can be omitted for a small built-in set. This provides meaningful guidance beyond 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 explicitly states it scans the local Decision Graph for four specific categories (uncovered components, weak rationales, contested decisions, derived staleness). This clearly distinguishes it from sibling tools like audit or decision_get, as it focuses on gap analysis of decision graph health.

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 provides a concrete usage recommendation: schedulers should call with digest_only:true and treat actionable:false as a no-op. This gives practical guidance, though it does not explicitly contrast with alternatives like audit tools or manual inspection.

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