validate_guids

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

Annotations only give destructiveHint=true, so the description carries real weight and delivers: it discloses that the tool generates fresh GUIDs, rewrites MaeExp.txt/xml files, populates CRC32 @CT_ hashes, and cleans dangling network metadata. This tells the agent what on-disk artifacts get mutated. It stops short of addressing reversibility, backups, or permission needs.

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 scan purpose is front-loaded, followed by the auto-fix actions in a well-ordered sequence. Three sentences, each contributing information with no filler. Slightly dense but not wasteful.

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 destructive-by-default mutation tool with no output schema, the description explains what changes but omits whether findings are reported back, whether fixes are reversible, and what the agent should verify before running with auto_fix=true. Adequate but with a notable gap around the default destructive path.

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 both auto_fix and lcp_path, including the 'omit to use currently selected project' fallback. The description reinforces the auto-fix behavior but adds no 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 specific verbs and resources: scanning a LASAL station project for duplicate GUID collisions and TO_UDINT(0) placeholders, plus auto-resolution. This is far more specific than a tautology and clearly separates it from generic siblings like inspect_project. It does not explicitly contrast with any named sibling, keeping it at 4 rather than 5.

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?

No explicit statement of when to use this tool versus alternatives, nor any prerequisites (e.g., when to call before/after build_project or deploy). Usage is only implied by the purpose text. There is no when-not guidance despite a destructive default behavior.

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