Backed: NEAR solvency checks

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

Read-only and open-world are already declared in annotations, so the description's added value is the same-block atomicity guarantee (owed and held read at one block, avoiding skew), the adapter auto-guessing behavior, and the applicability limit to backed_solvency contracts. The main undisclosed trait is the response shape, which matters since there is no output schema.

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 sentences, front-loaded with the core comparison, then the usage trigger, then the supported scope. Slightly padded by the explanatory aside "so the answer is exact," but no sentence is wasted.

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 3-parameter read tool with full schema coverage and safety annotations, the description covers purpose, trigger, atomicity, and supported protocols. The gap is that with no output schema, the agent is not told what the returned owed-vs-held comparison looks like, which is the one thing left to inference.

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 coverage is 100%, so baseline would be 3; the description earns above that by adding applicability constraints on `target` (must implement backed_solvency) and clarifying that `adapter` is auto-selected for the two known protocols with `backed` as fallback. It does not add anything about the tokens array or the 10-token cap.

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 and resource pair: reads a protocol's owed accounting view versus its held ft_balance_of for each token, at a single block. That is far more precise than the name alone and tells an agent exactly what question it answers. It does not, however, distinguish itself from sibling intents_backing_summary, so 4 rather than 5.

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?

"Use before depositing into a protocol" gives a clear triggering condition, and the supported-targets sentence scopes where it applies (intents.near, contract.main.burrow.near, any backed_solvency implementer). There is no explicit when-not guidance and no mention of the sibling summary/status tools as alternatives, which keeps it out of 5 territory.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description contributes real context by saying the values are what the contract 'last recorded' (i.e. stored state, not a live evaluation) and by enumerating the status categories, but it says nothing about freshness/staleness of that record or what 'owed', 'held' and 'block' represent.

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?

A single front-loaded sentence that packs the resource, the identity pair, the status enum and the returned fields with no filler. Nothing in it is redundant with the tool name or title.

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 four-parameter read tool with no output schema, the description covers the resource and result categories but omits how the returned values should be interpreted (units/types of owed and held, meaning of block) and gives no guidance on the optional checker/network overrides. It is adequate but leaves real gaps for correct interpretation.

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 coverage is only 50%: 'checker' and 'network' are documented in the schema, while 'token' and 'target' are bare. The description partly compensates by framing the input as a '(protocol, token) pair', implying target is the protocol identifier, but it leaves the meaning of 'owed', 'held' and 'block' unexplained and adds nothing about the default checker/network behavior.

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 names a specific verb+resource: reading what the on-chain Backed checker contract last recorded for a (protocol, token) pair, plus the exact result domain (Healthy/Suspected/Confirmed breach). It is clear on its own, but it never mentions the sibling tools check_backing or intents_backing_summary, so the agent gets no explicit differentiation between this recorded-status read and the live backing check.

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?

There is no statement of when to use this tool versus check_backing or intents_backing_summary, and no prerequisites or exclusions. The phrase 'last recorded' hints that this returns cached on-chain state rather than a computed answer, which could be a differentiator, but the reader must infer that and it is never spelled out.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-structured context: the data comes from a 'latest daily scan', telling the agent results may be up to a day stale rather than a live on-chain read — important for interpreting output. It stops short of describing latency, caching, or what happens if a scan is missing.

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?

A single sentence with zero filler that front-loads the scope ('latest daily scan of every NEP-141 token') before enumerating the three returned facts. Nothing is repeated from the title or schema, and 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?

With no parameters and no output schema, the description must carry the burden of saying what comes back, and it does: backed count, under-backed tokens with magnitudes, and reasons. The remaining gap is scope of history — whether only the latest scan is available or prior days can be retrieved — which matters for an agent deciding if this tool can answer a trend question.

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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. The description correctly implies no inputs are needed by framing the result as a fixed, global daily scan.

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 resource and scope: 'the latest daily scan of every NEP-141 token in NEAR Intents', plus the three things it reports (count backed, under-backed amounts, reasons). It is clearly an aggregate/overview tool, which implicitly separates it from the per-token sibling check_backing, but it never names or contrasts with siblings explicitly.

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?

Usage is only implied: 'every NEP-141 token' signals a broad overview use case, versus check_backing for a single token. There is no explicit when-to-use/when-not-to-use statement, no mention of checker_status, and no guidance on whether to call this first before drilling into an individual token.

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