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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered. The description adds operationally useful context about funding the returned address with the shielded asset plus native gas. It does not say what the return value looks like (format, chain prefix) or whether the address is stable across sessions.

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 short sentences, zero filler, with the core fact (this returns the wallet address) front-loaded and the funding hint following as supporting context. Every sentence 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?

For a zero-parameter read with rich annotations and no output schema, this is nearly complete; the funding guidance covers the main follow-up action. The only real gap is not characterizing the returned address format, which matters slightly because no output schema exists.

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 no parameters and the schema is trivially complete, so the baseline is 4. The description correctly implies a no-input read that simply yields the wallet address, leaving nothing ambiguous.

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 resource, the agent wallet's address, and is clearly distinguishable from siblings such as blackpool_balance, blackpool_send and blackpool_deposit. It lacks an explicit retrieval verb such as 'returns' or 'get', so it falls just short of the crisp verb+resource form.

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 gives an implicit use case: call this so you can fund the wallet with the asset to shield plus native gas before depositing. It never states when to call it versus blackpool_balance, nor any precondition such as needing the wallet initialized, so usage is inferred 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 readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so safety is covered. The description adds nothing beyond them: no statement of what data is returned, whether the result is static reference data or reflects live chain state, or what 'valid origins' means in practice. It does not contradict the annotations, but it contributes no behavioral context.

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?

It is a single short phrase with no padding, so nothing is wasted. However, it is concise to the point of being an incomplete sentence rather than a front-loaded explanation, so brevity costs clarity here.

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, no output schema, and annotations already covering the safety profile, the description is the only source of meaning about what this tool returns. It does not say whether the response is a list of bridgeable asset pairs, a mapping of origins per asset, or something else, leaving the tool's output shape entirely unknown.

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 and the description has no parameter semantics to explain, so the baseline of 4 applies. The mention of 'destination assets' and 'origins' hints at what the invisible output is keyed on, but no parameters exist to clarify.

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 'Bridge destination assets and valid origins' is a noun-phrase fragment that restates the title without a clear verb or object. It never says whether the tool lists bridgeable assets, returns supported origin/destination pairs, or performs a bridge. It also does nothing to distinguish itself from the sibling blackpool_bridge_quote.

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 when-to-use guidance, no prerequisites, and no mention of the obvious alternative, blackpool_bridge_quote, which an agent would need to choose between. The agent is left to infer usage entirely from the name.

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 bar is lower, and the description still adds real behavior beyond them: that both shielded and public balances are returned, that passing `pool` restricts results to a single private pool, and that `wait=true` blocks for up to 30 seconds due to eventual consistency after a deposit. It omits any mention of authorization requirements or the shape/ordering of returned balances.

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 with no filler, and the resource scope is front-loaded before the parameter caveats. The telegraphic "With pool:" fragment is terse to the point of being slightly cryptic, but nothing 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?

The tool is read-only with no output schema, so the description must carry the return-value burden; it says private and public balances come back but not in what structure, units, or whether zero balances are included. Combined with the unresolved question of which account is being queried, an agent has enough to call it but not to fully anticipate the response.

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 `wait` parameter has no schema description, and the description compensates well: "wait=true polls up to 30 s while a private balance reads 0 (right after a deposit)" explains semantics, latency and the triggering scenario. The schema already covers `pool` and `chain` (67% coverage), so the description only needed to fill the `wait` gap, which it does.

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?

"Private (shielded) and public balances" identifies the resource returned and the pool scoping rule, but it uses a noun phrase with no verb and never says whose balances are returned (the connected wallet vs. an address, which matters given the sibling blackpool_address). An agent can infer the core purpose but must guess at the subject of the query.

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?

No when-to-use guidance is given and no sibling is named: it is unclear how this differs from blackpool_assets or blackpool_address. The only conditional statement is about the `pool` parameter narrowing output to one pool, which is scoping rather than usage guidance.

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 destructiveHint=true, openWorldHint=true, idempotentHint=false, so the risk profile is known from structured data. The description adds genuinely new behavior: the transfer is private, and it returns upon submission rather than delivery unless wait=true — important for an async cross-chain operation. It still says nothing about fees, minimums, failed-route behavior, or irreversibility of a submitted transfer, which matters for a destructive tool.

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 compact sentences, purpose first, then parameter disambiguation, then return semantics — no filler. The semicolon-separated clauses and the pool enumeration are dense but each carries actionable information.

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 destructive, open-world mutation with no output schema, the description covers what it does, valid inputs, and when it returns, which is enough to call it correctly. Missing are quantitative context (fees, limits), error/failure handling for a cross-chain route, and any note on whether a submitted transfer can be recalled.

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 only 40% schema coverage, the description carries most of the burden and does it well: it enumerates the nine valid `from` pool values, points `dest_asset` at blackpool_assets, and explains that `recipient` is either an EVM 0x address or a Solana address when the asset is sol_*. Only `amount` is left to the schema, which already documents it thoroughly.

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 — 'Private cross-chain transfer via NEAR Intents' — which is far more than the title's restatement and clearly implies bridging rather than sending or swapping. It never names a sibling such as blackpool_send or blackpool_swap, so the agent must infer the boundary from the 'cross-chain' qualifier alone.

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 preconditions: `from` must be one of the enumerated private pools, and `dest_asset` must come from the blackpool_assets sibling, which routes the agent to the right lookup call before invoking this one. It stops short of explicit exclusions — nothing says to use blackpool_send for same-chain moves or when a bridge route is unavailable.

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?

The annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond them by disclosing the full status taxonomy (PENDING_DEPOSIT, PROCESSING, SUCCESS, REFUNDED, FAILED) and that each record carries a refund address, which tells the agent how to interpret results. It omits ordering, pagination and account-selection behaviour, 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?

A single front-loaded sentence with no filler; the status list is the most decision-relevant content and appears early. The phrasing 'every bridge ... with status (...) and refund address' is slightly elliptical but readable.

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 zero-argument read tool with no output schema, the description carries the burden of describing the return, and it only names two pieces of each record (status and refund address). Amount, source/destination chain, timestamps and ordering are unstated, so an agent cannot fully predict the shape of the response even though it can call the tool 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?

There are zero parameters, so the baseline is 4. The description usefully confirms the scope is implicit-account-wide ('this account') rather than requiring a filter, which is the only semantic an agent could get wrong here.

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 the resource precisely ('every bridge of this account') and enumerates the status values returned, so an agent can tell it is a history/listing read rather than the bridge-creation sibling blackpool_bridge. It stops short of explicitly contrasting itself with that sibling, so it stops at 4.

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: the enumeration of statuses like PENDING_DEPOSIT and PROCESSING suggests this is the tool to poll for bridge progress, but the description never states when to call it or what alternative exists. With blackpool_bridge and blackpool_recover as near neighbours, an explicit 'use blackpool_bridge to initiate a bridge' line would have removed the 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 flag this as destructive, non-idempotent, and open-world, so the description doesn't need to re-establish risk. It adds genuinely new behavioral facts: gas is paid from the agent wallet, execution takes 30-90 seconds, and a timeout is not evidence of failure, which directly addresses the non-idempotent hazard.

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 purpose, then cost, then timing and the retry warning. Every sentence carries distinct information with no 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?

For a destructive, open-world mutation with no output schema, the description covers cost, latency, and retry safety well, but never says what the call returns (transaction hash? receipt?) or whether it waits for confirmation. An agent can call it correctly but cannot predict the result shape.

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 amount, chain, and pool semantics (including the 'max' sentinel and per-chain pool options) are already fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 states a specific action (shielding/depositing funds) with a clear source (agent wallet) and destination (private pool), which is distinct from siblings like blackpool_send or blackpool_swap. It never names a sibling to contrast with explicitly, but the verb+resource+scope combination is unambiguous.

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 gives operational guidance (expect 30-90 s, don't retry on timeout without checking blackpool_balance) but no guidance on when to choose deposit over blackpool_send or blackpool_bridges, nor any stated prerequisites such as needing a funded wallet.

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 idempotentHint=true and destructiveHint=false, and "safe to run any time" is consistent with that, adding confirmation context. However, the description never explains what happens to burners with zero funds, whether gas is required on each chain, whether partial failures are possible, or what the call reports back — meaningful gaps for a funds-moving operation with openWorldHint=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?

A single front-loaded sentence with the action and destination first, then the safety note. The trailing parenthetical "(or to)" is slightly awkward, but nothing 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 two-parameter, zero-required, no-output-schema tool, the description covers the core action and destination adequately. It remains thin on return behavior, gas handling, and the meaning of "registered burner," which an agent would need to use it confidently across the five supported chains.

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 50% schema coverage, the `chain` enum is documented in the schema while `to` has only a regex pattern. The description's "(or to)" does add real meaning by framing `to` as an alternate sweep destination, but it does not say whether that address must be registered or whether the override applies across all chains.

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?

"Sweep every registered burner that still holds funds back to the agent wallet (or to)" names a specific verb (sweep) and resource (burner-held funds) plus the destination, which separates it from siblings like blackpool_send or blackpool_deposit. The only gap is the undefined term "registered burner," which an agent may not be able to resolve without external knowledge.

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?

"Safe to run any time" gives a rough usage signal but no explicit when-to-use versus when-not-to-use, and it never points to an alternative such as blackpool_balance for checking holdings or blackpool_send for targeted transfers. Usage is implied rather than stated.

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 flag destructive, non-idempotent, open-world behavior, but the description adds substantial context beyond them: the relayer pays gas, the fee is flat plus 0.35% deducted from the received amount, "max" splits across sends and leaves dust, and each send takes 30-90 s. The timeout retry warning is exactly the operational guidance an agent needs for a non-idempotent send.

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 purpose, then fee, then max semantics, then latency, then the retry hazard. Four compact sentences with no filler; each one changes how an agent would call the tool.

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 destructive, non-idempotent payment tool with no output schema, the description covers cost, timing, and failure handling well. It stops short of saying what a successful call returns (e.g., a tx hash or operation id) and leaves the flat fee amount unspecified, which an agent may need before committing funds.

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 75% and the description adds meaning on top, especially the "max" token behavior (whole pool balance, or every pool when pool is omitted) which the schema pattern alone does not convey. Recipient remains undocumented in both, but its regex constraint makes that low-risk.

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 and resource ("Pay any EVM address privately from the private balance"), which immediately separates it from siblings like blackpool_deposit, blackpool_swap, and blackpool_bridge. An agent knows exactly which operation this is without opening the 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?

It states the context of use (private balance payout), clarifies the "max" case including the multi-pool variant, and explicitly routes post-timeout behavior to blackpool_balance. It does not, however, explicitly say when to prefer blackpool_bridge or blackpool_swap instead, so the sibling routing is only partially covered.

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?

Beyond the annotations, the description discloses privacy, same-chain scope, re-shielded output, and recovery behavior on partial failure. It does not mention fees, rate behavior, or approval requirements, but it adds meaningful operational context for a destructive swap.

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 two short sentences, front-loads what the tool does, and immediately follows with the recovery path. There is no redundant or filler wording.

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 swap with no output schema, it covers the core operation, privacy behavior, same-chain constraint, and failure recovery. Minor gaps remain around slippage behavior and fee/rate expectations, but the essential invoke-and-recover guidance is present.

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 75%, so the schema already documents from, chain, and amount. The description adds no parameter-level meaning, and slippage_bps remains unexplained in both the schema and the description.

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 states a specific verb and resource: a private same-chain swap between the native pool and stablecoin pool, with re-shielded output. It clearly distinguishes same-chain swaps from bridge-related siblings, though it does not explicitly contrast with send or deposit.

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 gives a useful recovery instruction: if the swap stops halfway, run blackpool_recover. However, it does not explicitly say when to use this swap versus blackpool_bridge, blackpool_send, or blackpool_deposit beyond the same-chain constraint.

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