Open Solid

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

Annotations already declare destructiveHint=false, readOnlyHint=false and openWorldHint=false, so the description only needs to add delivery context. It does not say what the human actually sees, whether calling twice sends duplicate announcements (idempotentHint=false makes that a real risk worth flagging), or what the tool returns.

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, front-loaded with the action and followed by the ordering rule — no filler. However, the size reflects under-specification rather than disciplined editing; there is room for a clarifying clause without becoming verbose.

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 tool with no output schema, zero parameter documentation and a side-effecting notification, the description says almost nothing about outcome or semantics. An agent could call it correctly by luck, but not confidently predict what the human receives.

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 0% across two parameters, so the description carries the full burden and largely drops it. 'Tell your human' hints that a message may be sent, but nothing explains what agent_name is for, its expected format, or whether message overrides a default text.

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 concrete action and recipient: notify the human that the agent has connected, which clearly separates it from the payment/banking siblings. It stops short of explaining the mechanism (notification vs. message on a channel), but the intent 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?

'Call first' is an explicit ordering instruction that tells the agent when to use this tool relative to everything else — a genuine usage rule rather than an implied one. No exclusion cases or alternatives are given, but there are no plausible alternatives in this sibling set for a connect handshake.

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=false, so the safety profile is covered. The description adds one behavioral fact – results are limited to 'recent' activity – but does not say how recent, whether results are ordered or capped, or whether they are scoped to the authenticated account.

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 fragment with zero waste, which is good, but it reads as under-specification rather than deliberate economy. A verb-led sentence would have cost no more space and carried far more 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?

With no input parameters and no output schema, the description is the only place an agent can learn the return shape, and it only names three entity types without stating count limits, ordering, or the recency window. Adequate as a hint, insufficient as a specification.

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 there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The entity types mentioned are return content, not inputs, so no credit or penalty beyond the baseline.

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 enumerates what 'activity' consists of (payments, deposits, connections), which adds meaning beyond the tool name. But it is a bare noun phrase with no verb and no scope definition – 'recent' is undefined, and it does not distinguish itself from siblings like get_banking or list_recipients.

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 rather than get_banking, get_wallet, or list_recipients. The agent must infer from the returned entity types that this is the transaction-history view, which is a stretch given the terse phrasing.

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=false, so the safety profile is covered structurally. The description adds nothing beyond that: no note on what data is returned, whether transfers are included or a separate call, or any rate/auth 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 short and wastes no words, but the single fragment is under-specified rather than efficient — there is no verb-led statement of purpose to front-load. Brevity here comes at the cost of clarity.

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 is the only place to explain what comes back, and it does not — it is unclear whether it returns account numbers, a transfer list, or both. For a read tool in a crowded banking namespace, that leaves selection ambiguous.

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 there is no parameter semantics burden on the description. Baseline 4 applies for an empty 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?

The description is a noun fragment ("US bank account numbers and transfers") that largely restates the title "Get bank account" rather than stating an action. It hints at the returned resource but gives no verb and does not distinguish this from siblings like get_wallet or list_recipients.

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 guidance on when to call this versus the nine siblings, no prerequisites, and no exclusions. An agent must guess whether it needs get_banking or get_wallet to retrieve banking details.

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=false, so the safety profile is covered. The description adds the single-vs-list response-shape distinction, which is useful, but it says nothing about the meaning of card_type, result volume, or ordering/pagination for the list case.

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 short sentence with no filler, and the more specific mode (card_id) is placed where it is easy to spot. It is terse to the point of under-specification, 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?

With two undocumented parameters, no output schema, and no pagination or filtering context, the description is too thin for the tool's surface. An agent gets no guidance on what card_type does or what a list response looks like.

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 0%, so the description bears full responsibility for explaining parameters. It clarifies card_id (returns one card's details) but leaves card_type completely undefined — an agent cannot tell whether it filters by card type or selects a card variant.

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 indicates the resource (reloadable cards) and two retrieval modes: a list, or a single card's details when card_id is supplied. However, the verb is only implied by the name/title ('Get cards') and the phrasing 'Reloadable cards' is a noun fragment, so the purpose is inferable rather than stated outright. It does distinguish the list-vs-single behavior, which helps separate it from siblings like get_wallet or get_banking.

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: pass card_id for one card, omit it to get the collection. There is no explicit statement of when to use this tool versus get_wallet, get_banking, or list_recipients, and no prerequisites or exclusions are given.

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=false, so safety is covered. The description adds nothing beyond that — no statement of what the returned status values are, whether unverified accounts error or return a state, or whether the call requires the owner to be signed in.

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?

One short clause with no waste and the key qualifier (account owner) up front. It reads as an incomplete sentence, which is a minor structural flaw rather than verbosity.

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, so the description is the only place the return contract could be stated, and it says nothing about possible status values or what an unverified result looks like. For a status-query tool that omission is material.

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 empty, so there is nothing for the description to disambiguate. Baseline for a zero-param tool 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 fragment identifies the resource — the account owner's identity verification state — which distinguishes it from siblings like get_banking or get_cards. But it is a noun phrase with no verb and never says the tool retrieves or returns this status, so the action is only inferable from the 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?

No indication of when to call this versus related tools (e.g., after onboarding, before pay) and no prerequisites or exclusions are given. The zero-parameter read shape makes this low-risk, but no guidance is offered at all.

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 this is a read-only, closed-world operation, so the safety profile is covered. The description adds useful scope by saying it covers every payment type, but does not add details about authentication, rate limits, or response behavior.

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 a single front-loaded sentence with no wasted words. It states the scope and content directly.

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-only pricing lookup with no output schema, stating that it returns fees and limits for every payment type is nearly sufficient. The main missing context is how it relates to get_spend_limit, but the tool is otherwise complete enough to call.

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 there are no parameter semantics that the description needs to compensate for. The baseline for zero parameters is 4.

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 clearly identifies the resource as fees and limits across every payment type, which tells an agent what data the tool returns. It does not explicitly differentiate from the related sibling get_spend_limit, so it falls short of a 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?

There is no explicit guidance on when to use this tool versus alternatives such as get_spend_limit. The intended use is only implied by the phrase 'fees and limits for every payment type.'

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=false, so 'Read-only' in the description is largely redundant. The one substantive addition is that the limit is human-configured, which is real context, but nothing is said about staleness, units, or scope.

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 very short sentences with no wasted words, and the resource is stated first. It is arguably too terse, but nothing is padded or buried.

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 should say what the returned value looks like (a numeric amount? a currency-tagged object? null if unset?) and it does not. For a zero-parameter getter that is the main remaining gap.

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 there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter confusion is possible.

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 ('per-payment limit') and its origin ('your human set'), which distinguishes it from generic getters like get_banking or get_wallet. However, it doesn't clarify the relationship to the tool name 'spend limit' (total vs per-payment), leaving a small ambiguity.

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 indication of when to call this versus siblings such as get_pricing or pay. The 'Read-only' note implies a pre-payment check, but that workflow must be inferred 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 declare this as a read-only, closed-world operation. The description adds useful context about which chains and asset balances are returned, but it does not cover freshness, auth requirements, or multi-wallet behavior.

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 a single compact fragment that front-loads the most important information: wallet addresses and USDC balances. There is no wasted text.

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-only tool with annotations covering safety, the description provides enough signal about what data is returned. It could say more about response shape or wallet scope, but it is largely complete for this simple operation.

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 has zero parameters, so there are no parameter semantics to explain. The baseline for a parameterless tool is 4, and the description does not need to compensate for missing schema details.

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 the specific resource returned: wallet addresses on Solana and Base plus USDC balances. This distinguishes it from siblings like get_banking and get_cards, though it is written as a noun phrase rather than a verb-led statement.

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 gives no explicit guidance on when to call this tool versus alternatives such as get_banking or get_cards. Usage is only implied by the tool name and returned data.

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=false, so the safety profile is covered. The description adds that results are 'saved' recipients tied to a rail, which is mild context, but says nothing about ordering, pagination, or what happens when rail is omitted. With annotations carrying the safety burden, a moderate score is warranted.

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 tight sentence with the resource up front and the scoping values trailing; nothing is wasted. It is a fragment rather than a full sentence, but that costs nothing in clarity.

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 one-parameter read-only list tool with annotations and no output schema, the description covers the essentials. It still leaves the zero-argument case unexplained (does omitting rail list all recipients across rails?), which is the one behavior an agent needs to call it confidently.

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 0% and the schema declares no enum, so the description is the only place that defines the accepted rail values 'venmo, paypal or bank' — genuinely valuable. However, it never says whether rail is optional or what omitting it returns, which matters since the parameter is not required.

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 title plus description together state a specific resource (saved payout recipients) with a scoping dimension (rail) and enumerate its values. An agent can distinguish it from the singular get_* siblings (get_wallet, get_banking) since this is a collection listing. The verb is only implicit in the description body ('Saved payout recipients...'), relying on the title to say 'List'.

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 or when-not guidance, and no mention of any sibling alternative (e.g., using get_wallet for balances vs. this for payout targets). The only implied context is that 'rail' scopes the query, leaving the agent to infer that this is a pre-payment lookup step.

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, and idempotentHint=false, so the safety profile is known. The description adds value by disclosing that spend limits are enforced on the fee-inclusive total, that a one-sentence note is required, and that x402 payments return the API's response.

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 a single rambling paragraph that starts with an unnecessary 'PAID.' and packs multiple clauses without clear separation. It is adequately concise but not front-loaded or well-structured for quick parsing.

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 15-parameter destructive, open-world mutation tool with no output schema, the description is incomplete. It does not explain return values for non-x402 payments, does not cover most parameter semantics, and omits key behavioral details such as idempotency key usage or failure modes.

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 15 parameters and 0% schema description coverage, the description only explains the 'type' parameter (listing valid values) and the x402-specific parameters (url, max_usd, method, body). It leaves most other parameters (e.g., amount, currency, first_name, last_name, recipient_id, idempotency_key) undocumented, failing to compensate for the schema gap.

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 ('Make a payment') and resource ('from the wallet'), and enumerates the supported payment types. It clearly distinguishes this tool from the read-only siblings without needing to name them.

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 implied by the action and the note that a one-sentence note is always required. For the x402 type, it specifies to give url, max_usd, and optionally method and body, but it does not explicitly state when to use this tool versus alternatives (which are all read-only, so the need is minimal).

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