verify_hallucination_guard

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

With no annotations, the description carries the full burden and does well: it declares read-only ('does not modify source files'), idempotent/deterministic, and 100% offline, and it explains the return content. It stops short of only minor items like how mismatches are ordered or performance bounds.

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?

Front-loads the core purpose, then uses labeled Behavior/Usage/Returns sections that are easy to scan. Slightly verbose in places (e.g., restating read-only and offline separately), but every line is relevant.

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 verification tool, the description covers what it checks, how (AST against local symbol catalog), the safety profile, when to run it, sibling routing, and even the return shape. An agent has everything needed to call it 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 description coverage is 100%, so the schema already documents proposed_code, target_file, and project_root. The description adds only marginal framing ('against known workspace AST signatures') and doesn't add syntax or format detail beyond the schema, so the baseline 3 applies.

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 verb and resource ('Parses proposed code and verifies all internal imports and function/method call contracts') with concrete scope (argument counts, keyword parameter names, AST signatures). Clearly distinguishable from siblings like enforce_architecture_boundaries and audit_codebase_quality.

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?

Explicit 'When to use: Run BEFORE applying AI-generated code' with the failure modes it prevents, plus an explicit sibling route ('To enforce layer boundary separation rules, use enforce_architecture_boundaries'). Both when-to-use and alternatives are named.

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