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

Annotations mark this as a non-read-only, non-destructive, open-world write with idempotentHint=false; the description adds the crucial nuance that idempotency is conditional on supplying the same amount plus reference, and clarifies that omitting it always produces a new invoice. It also discloses the return payload (checkoutUrl). It does not mention auth, rate limits, or invoice expiry, so it stops short of full transparency.

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?

Four short sentences with the purpose front-loaded, followed by the idempotency rule and the follow-up tool. Every sentence carries distinct information and nothing is repeated from 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?

For a mutation tool with no output schema, the description covers the essential contract: what is created, the currency constraint, the deduplication rule, and the primary returned field. Missing lifecycle details (expiry, how the buyer receives the link) are minor given four well-documented parameters.

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 genuine meaning the schema lacks: reference functions as a deduplication key tying the same amount to the same invoice rather than just a webhook echo. The store and returnUrl parameters are left to their schema descriptions.

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 ("Creates a Stablevoy invoice") and bounds the scope (paid in USDT or USDC), then names the concrete artifact returned (checkoutUrl). It is clearly distinguishable from siblings get_invoice, list_invoices, and list_stores.

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?

Explicitly routes the agent: supply a reference when possible to avoid duplicate invoices, and use get_invoice to check status later. It gives a concrete naming example ("acme-october"). It does not discuss store selection or when not to create an invoice, leaving that to the schema.

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 cover readOnly, idempotent and non-destructive semantics, but the description adds genuine behavior: the store-scoping fallback (searches every connected store when omitted) and the not_found error when no store has the id. It also enumerates return fields, which matters because no output schema exists. It stops short of mentioning auth or rate-limit behavior, so not a full 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 purpose and scope, followed by return shape, then the store/error caveat, then the sibling redirect. The return-field list is dense but justified given there is no output schema, and no sentence is redundant.

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 read tool with no output schema, the description supplies exactly what is missing: the return payload shape (including nested payment fields and smallest-unit amounts), fallback scoping behavior, and the failure mode. Nothing an agent needs to call and interpret it correctly is absent.

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 goes beyond the schema by explaining where a valid invoiceId comes from and clarifying that omitting store triggers a cross-store search. Those are behavioral semantics the schema alone would not convey.

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+resource ("Gets one invoice by its id") and immediately scopes it to the case where the id is already known. It distinguishes itself from the sibling list_invoices by naming it directly as the lookup-by-criteria alternative.

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 when to use this tool ("when you already have the id, for example from create_invoice or list_invoices") and explicitly routes the agent elsewhere for status/reference/date lookups. That is a clear when/when-not pairing with the alternative named.

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, idempotentHint and destructiveHint=false, so the safety profile is carried structurally. The description still adds value by stating that settings are changed in the Stablevoy dashboard (telling the agent this is not the mutation path) and by enumerating the returned fields, which matters because 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?

Two sentences, front-loaded with the verb and resource before the field enumeration and the routing advice. The field list is long, but it substitutes for a missing output schema and each item is substantive rather than 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 single-parameter read tool with no output schema, the definition covers the return contents, the safe-read nature, and the escalation path from create_invoice. Nothing an agent needs in order to call it correctly 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?

There is a single optional parameter with 100% schema description coverage, and the schema already explains it accepts an id or exact name from list_stores and is only needed with multiple stores. The description adds nothing about the parameter, so the baseline of 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?

States a specific verb and resource ("Gets one store with its settings") and then enumerates the exact settings returned, so an agent knows the payload shape before calling. It also explicitly distinguishes itself from the sibling list_stores, which returns stores briefly.

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 a concrete triggering condition — "Call it first when create_invoice fails or a store cannot accept payments" — and names the alternative for the broader case ("use list_stores to see all stores briefly"). Both the when and the when-not are covered with a named sibling.

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, non-destructive, idempotent and open-world, so the safety profile is covered. The description adds genuinely new behavior: pagination is one page per call, nextCursor must be replayed with the same store, the response shape per store (name, invoices, nextCursor null on last page), and that no match returns an empty list rather than an error.

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 filters, then pagination mechanics, then the sibling pointer — a sensible order with no filler. The pagination sentence is somewhat run-on ("for each store its name, invoices ... and nextCursor"), costing some readability.

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 and eight optional parameters, the description covers what an agent needs: return shape, pagination protocol, multi-store behavior and error-free empty results. Nothing consequential is missing for correct invocation.

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 each of the eight parameters is already documented with types, bounds and enumerated values in the schema. The description adds marginal meaning beyond that — mainly the coupling of cursor with the same store and the semantics of omitting store — but does not restate filter formats or defaults.

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 ("Lists invoices") plus ordering ("newest first") and the governing condition ("to find invoices when you do not have an id"). It explicitly differentiates from the sibling get_invoice, which retrieves one invoice by id.

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 an explicit selection rule against the alternative ("Use get_invoice for one invoice by id") and clarifies the multi-store case ("Without store and with several stores, one page per store"). It even documents the no-match outcome so the agent does not mistake an empty page for failure.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's added job is return-shape disclosure, which it does with the enumerated fields (id, name, status, enabledNetworks, canAcceptPayments, evmPayoutStatus). It also usefully discloses a partial-failure behavior — an error entry for a store whose key no longer works — which annotations cannot convey.

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: what it does, what it returns including the failure mode, and how to sequence it. The field enumeration is dense but each item is distinct information, and the call-first instruction is front-loaded where the agent will act on 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?

There is no output schema, so the description must carry return values, and it names the exact fields plus the error case. Combined with annotations covering safety and idempotency, an agent has everything needed to call this correctly and interpret the result.

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. The description correctly spends no text on inputs and instead describes outputs, which is the right allocation for a parameterless list tool.

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 ('Lists the Stablevoy stores this server can work with') and scopes it ('this server can work with'), which also implicitly separates it from get_store, named later in the text.

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 explicit ordering guidance ('Call it first to learn store names for the store argument of the other tools') and names the alternative for the deeper case ('use get_store for the full settings of one store'). No inference is required from the agent.

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