QIE Wallet

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower, yet the description still adds real behavior: unresolved names yield an 'unresolved' status rather than a fabricated balance, and amounts come back as raw integers with a decimal formatting. It omits pagination/explorer-failure behavior, which keeps it from a 5.

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?

Front-loaded with the core action and scope, then address handling, then return format, then the advisory disclaimer. The price/APY sentence is longer than strictly needed but serves a deliberate guardrail purpose; no sentence is pure filler.

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 output schema, the description appropriately explains that results are raw integers plus a decimal rendering and what happens on unresolved input. Combined with full schema coverage and annotations, an agent has what it needs; only edge behavior on explorer/token-lookup failures is unaddressed.

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 is 3, but the description adds meaning beyond the schema by specifying that the address must be checksummed or all-lowercase hex and that QIE IDs resolve only on mainnet. The network and include_tokens semantics are left entirely to the schema, which already handles them well.

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 ('Read the native QIE balance and known token balances for an address') plus the exact chains supported (1990/1983), which is enough for an agent to distinguish it from qie_get_tx_status or qie_list_tokens without opening a schema.

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?

Gives clear context: use for balance reads on mainnet or testnet, accepts hex or a QIE ID on mainnet, and explicitly declines price/APY/yield questions. It also notes that QIE-ID resolution mirrors qie_resolve_name, which routes the agent correctly, though it never states an explicit 'use X instead when' exclusion for the sibling tools.

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 readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds genuinely non-redundant behavior: results are "pinned" facts, caller-supplied RPC URLs/chain IDs are rejected, and out-of-scope financial questions are actively declined rather than answered. It does not describe the response shape or caching/staleness of the pinned data, which keeps it from a 5.

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?

Core content is front-loaded and the scope disclaimer is well placed, but the sentence "Example QIE ID: yourname.qie" is off-topic for a network-metadata tool (that belongs to qie_resolve_name) and directly after a list of return fields, making it read like a returned value. There is also mild duplication of the chain-ID mapping already in the schema.

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 one optional enum parameter, no output schema, and full annotation coverage, this definition covers what an agent needs: what is returned, which networks exist, and what inputs are refused. The only gap is the absence of return-structure detail, minor here because the value set is small and enumerated in prose.

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 description coverage is 100% and the single enum parameter already documents mainnet=1990, testnet=1983, and that raw chain IDs or RPC URLs are rejected. The description mirrors that information rather than adding new meaning, so it earns the baseline 3 rather than more.

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 gives a specific verb ("Return") and enumerates exactly what resource is returned: chain ID, name, RPC URLs, explorer URL, native currency, scoped to QIE mainnet (1990) and testnet (1983). An agent can distinguish this from qie_get_balances, qie_get_tx_status, or qie_resolve_name purely on the description, since none of those return static network metadata.

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 states a clear when-not ("does not give price, APY, returns, yield, or investment advice and will decline such questions") and a hard input constraint ("The caller cannot supply an RPC URL or chain ID"), which prevents a common misuse. It stops short of naming sibling tools as the alternative when a caller actually wants balances or name resolution, so routing is left to inference.

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 readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuine value beyond them: it discloses the 'not found' outcome, the fields returned (block number, confirmations, from, to, value, token transfers, explorer link), and the dependency on what the explorer reports. The stray 'Example QIE ID: yourname.qie' is unexplained and slightly muddies an otherwise precise behavioral picture.

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 lead sentence is well front-loaded and information-dense, but the description carries two pieces of filler: an unexplained 'Example QIE ID: yourname.qie' that is irrelevant to a transaction-hash lookup and risks confusing an agent, and a boilerplate financial-advice disclaimer. Both consume space without helping the call.

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 output schema, the description steps in to describe the return payload and the possible 'not found' state, which is the main completeness risk for an open-world lookup. It also pins the two supported networks. Only the unexplained QIE ID example leaves a loose end an agent could misread.

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 description coverage is 100%, so both txHash and network are already fully documented, including the hash format and the chain-ID mapping. The description's mention of chain 1990/1983 merely restates the network field's schema text and adds no new semantics. 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?

States a specific verb and resource ('Read whether a transaction is pending, successful, failed, or not found') and enumerates the possible outcomes, which is exactly the mental model an agent needs. Scoping to QIE mainnet/testnet and the note that it does not submit transactions cleanly separates it from write-path or balance/name siblings.

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 establishes clear context (look up a tx by hash on a pinned network) and adds an explicit boundary: 'This does not submit a transaction.' It stops short of naming alternatives (e.g., use qie_get_balances for holdings, qie_resolve_name for addresses), so routing is implied rather than 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 readOnly, idempotent, openWorld, non-destructive, so safety is covered. The description adds real behavioral context beyond that: two data sources, a hard cap of 50 results, no price data, and an explicit refusal policy for price/APY/yield questions. It does not describe the result shape or pagination, which is why it is not a 5.

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 first two sentences are tight and front-loaded, but the closing disclaimers overlap: 'do not include prices', 'Not a price or yield question' (in the schema), and the APY/returns/yield/investment-advice refusal restate the same boundary in three places. Trimming to one disclaimer would strengthen it.

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, fully optional, read-only listing tool with rich annotations and no output schema, the description covers source, scope, cap, and refusal behavior. The main residual gap is that with no output schema, the return fields per token (symbol, name, address, decimals?) are not hinted at.

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 description coverage is 100%, so limit, query, and network are already well documented, including enum values and chain IDs. The description largely restates that (symbol or name matching, networks, 50 cap) and only adds the useful clarification that a .qie name is not a valid query. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource ('List tokens') and pins scope to QIE mainnet (chain 1990) or testnet (chain 1983), plus the data source (configured token list or network explorer). It is clearly distinguishable from siblings like qie_get_balances, qie_get_network_info, or qie_resolve_name.

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 states what the optional query matches (symbol or name) and explicitly warns that a QIE ID like yourname.qie is not a token query, which steers agents away from a common misuse. However, it never names an alternative tool (e.g. qie_resolve_name for IDs) or states when not to use this tool beyond out-of-scope price questions.

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 readOnly/idempotent/non-destructive/openWorld, and the description goes well beyond them: it discloses the record-store ordering (free then paid), proxy-implementation verification, that a missing record yields 'status ok' with 'address null', the optional otherChainAddresses field and its on-chain consistency requirement, and that no address is guessed. That is exactly the behavioral context an agent needs.

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?

Front-loaded with the core operation and then layered with constraints in a logical order; nearly every sentence carries information. The closing investment-advice disclaimer is boilerplate adjacent to the tool's purpose but is defensible as a guardrail.

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 output schema, the description carries the return-value burden and does so: it explains the success shape, the null-address case, the unresolved-on-testnet case, and the optional cross-chain field. Nothing an agent needs to call or interpret this tool is missing.

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 the baseline is 3, but the description adds real meaning: a bare label gets '.qie' appended, and the network is pinned to mainnet/testnet with raw chain IDs or RPC URLs rejected. Only the maxLength/format constraints are left to the schema.

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 ('Resolve a QIE ID ... to its QIE address'), names the input form (yourname.qie) and the chain (1990). The forward-resolution framing distinguishes it implicitly but clearly from the sibling qie_reverse_lookup.

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?

Gives useful situational context: testnet lookups return 'unresolved' because QIE ID isn't deployed there, and the network parameter is pinned rather than accepting arbitrary RPC/chain IDs. However it never explicitly names qie_reverse_lookup as the alternative for the inverse operation, so sibling selection is left to inference.

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 read-only, idempotent and non-destructive, and the description adds substantial behavior beyond that: the resolution ordering, the optional QIE ID API fallback with free names first, the reverse-resolution verification against a published record store, and the guarantee that no name is guessed. Failure modes (null name, unresolved on testnet) are spelled out rather than left for the agent to discover.

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?

Front-loaded with the core purpose, then ordered by resolution path and failure cases, which is easy to follow. The closing sentence about price, APY, yield and investment advice is a policy guardrail rather than lookup semantics and slightly dilutes an otherwise tight definition.

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?

There is no output schema, and the description compensates by describing the returned shape (status ok with name null, status unresolved) and the conditions producing each. Combined with the resolution rules and fallback chain, an agent has enough to call it and interpret results without further documentation.

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 the baseline is 3, but the description adds meaning beyond the schema by explaining the semantic consequence of the network parameter: testnet lookups return status unresolved because QIE ID is not deployed there. The address parameter itself is not elaborated beyond the schema's hex-address note.

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 ('look up the QIE ID ... for an address on QIE mainnet') and pins the chain (1990), which immediately distinguishes it from the forward-direction sibling qie_resolve_name. It also clarifies what value is returned when several names exist (owner's default, else the free QIE ID held).

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?

Gives clear conditions where the tool is the right call and where results will be empty: no QIE ID yields status ok with name null, and testnet (chain 1983) yields unresolved. It never explicitly names qie_resolve_name as the forward-direction alternative, so the when-to-use-vs-sibling routing is only implied.

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