find_group_usage

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

Annotations already indicate safe, idempotent, read-only. Description adds caching behavior (operates over cached corpus, no HTTP unless refresh:true) and return format (references with why_matched breadcrumbs), providing useful behavioral context beyond 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 plus bolded use-case and sibling contrast. No wasted words, well-structured with action, return format, usage guidance, and alternatives.

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?

Covers return format, caching, use case, and alternative tool. Without output schema, description provides enough context for effective use. Could mention that references contain entity type/ID but not required.

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 parameters are documented. Description adds meaning to 'refresh' by explaining it bypasses cache, which is helpful context beyond the schema's description.

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?

Description clearly states 'Find every reference to an agent group across triggers, automations, views, and SLA policies' with specific verb+resource+scope, and distinguishes from sibling 'audit_trigger_health' by noting it checks orphans including dangling group ids.

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?

Explicitly calls out 'The right tool for "is it safe to delete this group?"' and contrasts with 'audit_trigger_health' for broader orphan detection, providing clear when-to-use and alternative.

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