OrbitWan.io

WanBridge custody-vs-liability observations

get_bridge_solvency

Read-only

WanBridge custody-versus-liability observations from the newest finished recorder run, per token component. Every component carries a state: COMPLETE (every custody and liability site read), FLOOR (some custody sites unread, ratio_floor is a lower bound only), UNREADABLE (a site did not answer), NO_LIABILITY (nothing bridge-issued to back). ratio is present only for COMPLETE. A FLOOR ratio must never be read as the true ratio. A component with any liability site unread has state UNREADABLE and no ratio or floor. A FLOOR or UNREADABLE component carries blocked_by, naming what stopped a full reading (for example coverage). run carries the below_1 summary: the COMPLETE components whose ratio is under 1, with the complete_below_1 and complete_at_or_above_1 counts. run and every component are returned exactly as the recorder route sent them. Observations only.

Input Schema

Name	Required	Description
`limit`	No
`state`	No
`symbol`	No
`history`	No	with symbol: that component across the newest N finished recorder runs, newest first (1 to 200)

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 27, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / history / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / history / minimum
```
Added value: +-9007199254740991
```
- addedInput schema / properties / limit / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / limit / minimum
```
Added value: +-9007199254740991
```

Changed1 schema field changedOct 22, 2026

addedInput schema / properties / history

Added value: +{
+  "description": "with symbol: that component across the newest N finished recorder runs, newest first (1 to 200)",
+  "type": "integer"
+}

AddedSep 3, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, yet the description still adds substantial behavioral context: the four states and what each means, that ratio exists only for COMPLETE, that a FLOOR ratio is a lower bound only, and that blocked_by names the blocker. The caveat 'A FLOOR ratio must never be read as the true ratio' is exactly the kind of misinterpretation guard the description should carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the result semantics, and nearly every sentence contributes a rule an agent could otherwise get wrong. Minor redundancy in restating UNREADABLE twice, and 'returned exactly as the recorder route sent them' is thin added value, but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so well, covering states, ratio availability, blocked_by, and the run-level below_1 summary. The remaining gap is operational: no mention of pagination via limit, ordering of components, or how the history mode changes the response shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25%, so the description must compensate. It does explain the state enum values in detail, which is the highest-risk parameter, and 'per token component' plus the history schema description cover symbol indirectly. However, the limit parameter, result ordering, and whether state/symbol filters are inclusive are never addressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and scope: custody-versus-liability observations from the newest finished recorder run, per token component. The 'recorder run' framing implicitly distinguishes it from the sibling get_bridge_solvency_live, but that sibling is never named, so the differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus get_bridge_solvency_live, get_bridge_activity, or get_chain_coverage. 'Observations only' hints that it is a read of recorded data, but no condition, prerequisite, or exclusion is stated.

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

All OrbitWan.io tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?