apply_verified_patch

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

With no annotations, the description fully bears the burden. It details the offline, deterministic nature, the gates (patch-policy, verify_fix, blast-radius), and the specific conditions for approval (in-policy, clears finding, no new finding, no network/exec sink, bounded size). It explicitly states it does NOT write the file, eliminating ambiguity.

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?

Three sentences cover all essential information: purpose, inputs, criteria, and limitation. No fluff; every sentence serves a clear purpose.

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 complexity and lack of output schema, the description adequately conveys success conditions and tool behavior. It could be more complete by describing error responses or failure cases, but it is sufficient for an agent to invoke correctly.

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%, but the description adds critical meaning: it clarifies that newContent must be the FULL corrected content (not a diff), and that finding must include ruleId and location.file. This guidance goes beyond the schema descriptions.

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 clearly states the tool deterministically verifies a proposed fix before writing, with specific verb 'VERIFY' and distinct resource. It differentiates from siblings like get_fix_examples, inventory_crypto, and list_rules by focusing on verification.

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 explicitly tells when to use: when you have a proposed fix to verify, and it provides input requirements (finding, originalContent, newContent). It also clarifies the tool does not write the file, implying the agent must write after approval. However, no explicit when-not-to-use or alternatives are mentioned.

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