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

Above the annotations (readOnly, idempotent, openWorld, non-destructive), the description adds behavioral facts: the transaction must be 'indexed', the graph root is the sender, the output includes 'trace roots plus the graph and an explicit edge', and there is a limitation regarding 'mixed balances'. These details are not captured by annotations and materially improve the agent's understanding of side effects and constraints.

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 sentences: the first front-loads the core behavior and outputs, the second adds the use case and limitation. No filler, no repetition of schema or annotation data. Every clause earns its place.

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?

The tool is a graph-tracing tool with 8 parameters, a rich output schema, and strong annotations. The description explains the high-level algorithm, root selection, and a key limitation. However, it completely fails to explain the parameter semantics, especially since the schema parameter descriptions are all tautological. The agent would know what the tool does but not how to properly configure depth, direction, or value filters without external knowledge.

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?

Although the schema lists 8 parameters, every description is tautological ('Value for the depth parameter', etc.) providing zero semantic value. The tool description itself does not explain the meaning or interplay of depth, maxEdges, maxNodes, direction, minValueWei, or timestamps. Only txHash is implicitly referenced via 'indexed transaction'. With no meaningful schema coverage and no description compensation, parameter understanding is severely lacking.

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 uses specific verbs ('Loads', 'uses', 'returns') and names the resource ('XGR transaction relation graph') with clear output elements ('sender/recipient trace roots', 'explicit edge to highlight'). It also distinguishes the tool from siblings like trace_xgr_value_flow by stating what it does NOT do ('does not attribute later mixed balances to the seed value').

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 description explicitly states when the tool is useful ('following native XGR transaction relations') and provides an exclusion ('does not attribute later mixed balances to the seed value') that implicitly directs users to alternative tools when they need balance attribution. It does not name sibling tools directly, but the context is clear enough for an agent to make a reasonable selection.

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