Sheet: Manage Xrefs

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

Annotations only declare destructiveHint=true, and the description goes well beyond that: it discloses that detach removes exactly the counted inserts, that headless inserts counts model and paper space alike, and that on the live engine inserts and kind are deliberately null rather than fabricated. This is exactly the kind of side-effect and data-fidelity disclosure an agent needs for a mutation tool.

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 core scope statement is front-loaded, followed by engine behavior, refusal cases, and null semantics in a dense but organized block. Every sentence carries information, though the run-on sentences around the live-engine null behavior could be tightened slightly.

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 needn't be described, yet the description still explains the meaning of the returned inserts/kind fields across engines, plus all refusal modes. For a five-action, dual-engine tool with a destructive hint, this leaves no significant gap 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 100%, so the schema already documents name ('ignored by list') and new_path ('required by path'). The description restates the 'path needs new_path' constraint but adds no syntax, format, or value-range detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 opening line states the resource and unit of work ('One operation on one external reference'), and the body enumerates the exact five actions (list, reload, bind, detach, path). This cleanly separates it from the sibling xref_attach and from generic entity tools.

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?

It gives explicit engine-dependent routing: reload and bind require a live AutoCAD seat and are refused headlessly with capability 'xref_live', while list/detach/path work on both engines. It also names the refusal conditions (unknown action, unknown xref name, 'path' with no new_path). It stops short of naming alternative sibling tools, so it is clear context rather than full when/when-not guidance.

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