get_errors

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the queue-read semantics and the 20-entry cap, but omits the critical fact that the schema's `clear` parameter defaults to true, meaning a plain call silently clears the queue it just read. That destructive-by-default behavior is exactly what an agent must know.

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?

Two short sentences, front-loaded with the action and resource, with no filler. Nothing here is wasted text.

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?

An output schema exists so return values need not be explained, but for a tool whose unsurfaced default argument wipes the error queue, the description should at minimum warn about the clearing behavior and note when to use it versus the other status tools. Those omissions make it incomplete for correct invocation.

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% and the single `clear` boolean parameter is never mentioned in the description. Since `clear` defaults to true and changes whether the queue is wiped, the description's silence on it is a real gap rather than harmless brevity.

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 ('Read the instrument error queue') and even pins the exact SCPI query (:SYSTem:ERRor?), so an agent knows precisely what this does. It is distinguishable from siblings like get_status, get_ieee488_status, and clear_status, which target different status registers/queues.

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 by the tool name and the error-queue semantics (poll after sending commands), but the description never states when to prefer this over get_status, get_ieee488_status, or clear_status, nor when a read is appropriate. No alternatives are named.

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