xae_links

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

Annotations only say readOnly/non-destructive, but the description discloses far more: data provenance (instance XML vs. ProduceMappingInfo vs. RestoreInfo in .tsproj/.xti), a partial-read failure contract ('unlinked_count null, never counted as 0'), and the not_restored category that the main mapping table omits. That is exactly the kind of beyond-annotation disclosure this dimension rewards.

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 purpose is front-loaded correctly, but the body is dense and fragmentary, layering em-dash asides and a mid-sentence 'not_restored:' clause that reads like a schema note pasted into prose. Every element is informative, but the packing makes it harder to scan than it needs to be.

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 an output schema present, the description needn't document return structure, and it instead covers the non-obvious parts: where each link category comes from, how unreadable data is reported, and why not_restored links are missing from the mapping table. Nothing essential is missing for a correct call.

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 0% — the single parameter is an undescribed string. The description compensates by enumerating the accepted path forms (plc_path, iec_project_path, instance_path), which the schema does not convey. It stops short of saying which form is preferred or how paths are rooted.

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 resource (AT %I*/%Q* variable links of the PLC instance) and the concrete outputs it lists: linked targets from ProduceMappingInfo, unlinked variables, and orphaned links. It never names the adjacent xae_link / xae_unlink / xae_links_import siblings, so the agent must infer read-vs-write routing from the plural name alone.

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?

Usage is implied rather than stated: 'the usual reason an output never moves' signals this is a diagnostic call for dead outputs, but there is no explicit when-to-use/when-not or pointer to xae_link for creating links. An agent would still likely pick this over xae_link, but by name inference, not by instruction.

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