tia_apply_hmi_import

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

Annotations only flag destructive, non-idempotent, non-read-only. The description adds substantive behavior beyond that: backup of the original object, baseline recheck under exclusive access, import/compile/read-back sequence, absence of download, and the consequence that failure can leave unsaved engineering changes. The 'never replay a token' warning adds real operational safety context.

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?

Four short sentences, front-loaded with the action, then preconditions, then behavior, then risk. No filler and no repetition of the schema or annotations.

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?

Behavioral and safety context is strong for a destructive, non-idempotent mutation with no output schema. However, with zero schema coverage on all three required parameters, an agent still cannot determine what values to supply or how to obtain the token and hash, leaving a material gap for a one-shot destructive operation.

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% on three required parameters, so the description must carry the meaning and largely does not. 'Never replay a token' hints at single-use semantics for confirmToken, but planSha256 and the approval literal are unexplained, and there is no pointer to where the token or hash originates.

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 with qualifiers: 'Apply an explicitly approved exact HMI import plan once.' The 'exact HMI import plan' and 'No download' phrasing distinguishes it from the broader apply/import siblings without naming one explicitly, so an agent can identify what it does even if the boundary with tia_apply_hmi_project is left to inference.

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?

'once', 'explicitly approved', and 'never replay a token' give clear preconditions and a hard usage constraint. Missing is an explicit statement of which sibling produces the plan/token or when to prefer this over tia_apply_import or tia_apply_hmi_project, so guidance is strong on how but not on alternatives.

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