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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety is covered; the description adds genuinely new behavior such as the 'unknown' bucket for unmatched names and the local-execution/no-code-egress model. The data-retention details are relevant but partly generic product boilerplate rather than tool-specific behavior.

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 core purpose and the audit_stack routing are correctly front-loaded, but the trailing data-handling sentence runs long with an enumerated list of stored fields that crowds the tool's actual function. It is readable but not tight.

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?

For a zero-required-param, read-only getter with no output schema, the description covers what is returned (rule categories), the fallback behavior, and the privacy boundary, which is enough to call it correctly. It stops short of describing the shape of an individual rule, a minor gap.

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% with a single optional 'vendors' parameter, so the schema already carries the semantics (id or name, default all). The description adds only an indirect hint via the 'unknown' fallback and does not explain the id-vs-name distinction. Baseline 3 is appropriate.

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?

States a specific resource and its scope: detection rules for paid services in a codebase, enumerated as package names, env var patterns, config files, API hosts and feature patterns across ~100 vendors. An agent can distinguish this from siblings like get_recipe or search_recipes without opening any schema.

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?

Gives explicit workflow context: apply the rules locally, then send only vendor and feature names to audit_stack, never code or secret values. That routes the agent to the correct sibling and states the constraint, though it does not name a when-not-to-use condition.

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