aleph_xref_results

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

The description explicitly says this is read-only and that it does not trigger a new cross-reference computation, which adds useful behavioral context beyond the annotations. It is consistent with the readOnlyHint and destructiveHint annotations, and no contradiction exists.

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 concise sentences each earn their place: what the tool returns, when it is useful, and a behavioral caveat about not starting a new run. The main verb and resource are front-loaded.

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 simple read-only paged tool, the description plus full schema covers the purpose, inputs, and side-effect profile. It could mention behavior when no cross-reference results exist, but that is a minor gap given the schema and annotations.

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?

The input schema already includes descriptions for all three parameters, including defaults and bounds for limit and offset. The description adds contextual framing about the collection but does not need to compensate for missing schema information, so baseline 3 is appropriate.

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 states a specific verb ('Read') and resource ('cross-reference results already computed'), explains what those results are (entities resembling entities elsewhere in Aleph, scored and ranked), and clarifies that this is distinct from starting a new cross-reference run. This clearly differentiates it from related sibling 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 a concrete use case: finding overlaps between your own casefile and public registries. It also clarifies that this tool does not start a new cross-reference run. However, it does not explicitly name alternative sibling tools or state when not to use this tool.

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