xref_reload

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

With only readOnlyHint=false in the annotations, the description carries most of the burden and does disclose the key trait: it updates referenced geometry from disk. It also surfaces a security/safety constraint on the source path. It does not say what happens when the source falls outside allowed roots (error vs. silent skip) or whether local edits to the XREF are discarded.

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 short, labeled sentences (main behavior, Side-effects, Disambiguation) with the core action front-loaded. Every sentence carries distinct information with no restatement of the tool name.

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?

For a one-parameter tool with an output schema, the description covers the essentials: trigger condition, side effect, and the allowed-roots constraint. The remaining gap is failure semantics when the precondition is violated, which an agent would want to know before calling.

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% and the single 'name' parameter is already documented as the attached XREF to reload. The description adds only indirect meaning ('one existing XREF', 'resolved source'), so the baseline 3 applies rather than added value beyond the schema.

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 (Reload) and a bounded resource (one existing XREF), which cleanly separates it from sibling operations like xref_attach, xref_unload, and xref_detach. The scope qualifier about resolved source staying inside allowed roots further pins down what this call will and will not do.

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?

The Disambiguation line gives an explicit trigger condition: use when an external file has been updated on disk. The allowed-roots precondition also implicitly states when the call is not permitted. It stops short of naming sibling alternatives (e.g. xref_unload/xref_detach) for contrast, so it is strong but not exhaustive.

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