tia_create_hmi_import_plan

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

readOnlyHint=true is consistent with the 'read-only' claim, and the description adds real behavioral context beyond annotations: it captures a live baseline, a full exact diff, compile/save scope, and an immutable one-time approval token, and it rejects renamed objects and changed external references. However, the presence of a saveProject parameter with default false sits in tension with an unqualified 'read-only' framing, and the description never explains that relationship.

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 dense sentences with the identity and scope front-loaded, followed by what the plan captures and its rejection rules. No filler, though the third sentence's rejection criteria could be tightened.

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?

With no output schema, the description does reasonably describe what the plan payload contains (baseline, diff, compile/save scope, approval token), which is the most important missing piece. But for an 8-parameter tool with zero schema descriptions, the complete absence of parameter guidance and of any stated relationship between this plan and the sibling apply tools leaves real gaps.

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 0% across 8 parameters (7 required), so the description must carry the explanatory burden and largely does not. Only the screen/template enum and the saveProject flag are obliquely touched ('classic V20 screen/template', 'compile/save scope'); processId, processStartTimeUtc, projectPath, targetPath, objectPath, and especially candidateXml (25 MB max) are left entirely unexplained.

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 names a specific verb and resource ('exact plan for replacement of one existing classic V20 screen/template') and pins down the scope as replacement of exactly one existing object, which distinguishes it from generic import-plan siblings. It never names an alternative sibling explicitly, so differentiation relies on the reader inferring from 'replacement' and 'classic V20'.

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?

Mentioning an 'immutable one-time approval token' implies this is a pre-apply planning step, but the description never says when to pick this over tia_create_import_plan, tia_create_hmi_project_plan, or tia_create_unified_hmi_edit_plan, nor does it point to tia_apply_hmi_import as the follow-up. Usage is implied rather than stated.

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