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

Goes far beyond annotations by detailing state semantics (COMPLETE, FLOOR, UNREADABLE, NO_LIABILITY), clarifying that FLOOR ratios are lower bounds only, defining blocked_by, and explaining the run summary. It also discloses data fidelity ('returned exactly as the recorder route sent them'). No contradiction with readOnlyHint=true.

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 description is dense but well-structured: it front-loads the main purpose, then explains states, ratio rules, and summary in a logical order. Every sentence adds necessary information without redundancy, though length is justified by complexity.

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?

Given the absence of an output schema and the complexity of state-dependent fields, the description thoroughly covers return semantics: states, ratio presence, blocked_by, run summary, and fidelity. An agent has sufficient information to interpret responses correctly.

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?

With 0% schema description coverage, the description compensates by explaining the 'state' parameter thoroughly with enum meanings and behavior. 'symbol' is implied via 'token component' but not explicitly linked. 'limit' is not addressed. Partial but not complete compensation for all parameters.

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 precisely identifies the tool as returning WanBridge custody-vs-liability observations per token component, with detailed state explanations. It clearly distinguishes from sibling tools like get_bridge_activity (activity vs solvency) and sets expectations about data origin and structure.

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 implies usage for custody/liability analysis but does not explicitly state when to use this tool over alternatives or provide exclusions. It references 'Observations only' and data from recorder runs, but lacks direct comparison with sibling tools or conditions indicating alternatives.

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