ServGhost

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

With no annotations, the description itself must indicate behavioral traits. It communicates that the tool is a read-only lookup ('Return the current USD balance') and that it is useful for checking funds before ordering. It does not disclose error behavior, token validation, or what the returned payload looks like, so it covers the basics without being rich.

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-load the core behavior and then give a decision rule. There is no filler or repetition, and every sentence adds value.

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 single-parameter tool, the description provides the essential purpose and a clear usage context, and the sibling list supports routing. It does not describe the return format or failure cases, and there is no output schema to compensate, so it is slightly incomplete but still adequate for typical use.

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 schema has 0% description coverage, and the tool description does not explain the account_token parameter beyond the phrase 'for an account'. The token name is somewhat self-explanatory, but the agent is not told what the token represents, where to obtain it, or how it is used, which is a meaningful gap for a required parameter.

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: it returns the current USD balance for an account. It also frames this against related actions (create_order, topup_create), making the tool's purpose immediately clear and distinct from the listed 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?

It explicitly says when to use this tool: to decide whether to call create_order or topup_create first. This gives the agent a concrete decision rule and mentions the relevant alternatives by 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?

With no annotations provided, the description carries the behavioral disclosure burden. It clearly communicates an informational, read-only behavior: returning a canonical recipe and examples. Since there are no parameters and the tool merely outputs guidance, this is sufficient disclosure of the core behavioral trait; no side-effect or authentication warnings appear necessary for a zero-side-effect help 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?

The description is a single, front-loaded sentence that states what the tool returns and when to use it. Every clause earns its place, and there is no redundant or filler content.

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, informational tool with no output schema, the description is complete. It tells the agent what to expect (a recipe and examples) and when to call it. No additional context is required 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?

The input schema has zero parameters specialized 100% by an empty object, so there is no parameter semantics to explain. The rubric baseline for 0 parameters is 4, and the description appropriately adds no redundant parameter detail.

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 uses a specific verb ('Return') and a clear resource ('canonical 4-call recipe for buying a server, with examples'). It also distinguishes itself from the sibling server-purchase tools by presenting itself as the meta-help entrance point, so an agent can immediately tell this is not another account, order, or server action tool.

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 explicitly states when to invoke the tool: 'Call this first if you are unsure how to use the tools.' It provides clear contextual guidance, though it does not name specific sibling alternatives or cases where the tool should not be used, which would push it to a 5.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states that the server is paid from balance, that a topup must confirm first, that insufficient balance returns a structured response with deficit and suggested amounts, that omitting account_token creates a new account whose token must be stored, and that the server is active immediately.

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 dense but front-loaded, with the core constraint stated first. Every sentence carries a distinct operational fact: topup prerequisite, insufficiency-handling flow, account-token behavior, and immediate activation. The length is justified by the payment and retry complexity.

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 9-parameter, payment-dependent tool with no output schema, the description covers the critical lifecycle: required topup, error/retry shape, account creation, and immediate activation. The main gap is that the successful return payload is not described and there is no reference to siblings like list_plans or list_locations for populating required fields, but the core flow is largely complete.

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 description adds real meaning for account_token — saying a missing token triggers account creation and requires storing the returned token — which goes beyond the schema's 'optional Bearer token.' However, the overall parameter coverage is only partial, and required plan and location values remain undocumented in both the schema and the description, so the gains are uneven.

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: 'Deploy a server from your USD balance.' It also distinguishes itself from siblings by declaring the BALANCE-ONLY constraint and referencing topup_create and topup_bonus, so an agent can clearly separate the creation flow from quote, server_action, or account_balance.

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 an explicit prerequisite: 'you must topup_create first (min $30, see topup_bonus for free credit tiers), wait for the topup to confirm, then call this.' It also defines the retry path when insufficient_balance is returned, effectively telling the agent when not to proceed and what to do instead.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool lists jurisdictions, which implies a read-only operation with no side effects. It does not describe the output format or any special behaviors, but for a simple list operation this is adequate. The description is honest and does not contradict any hidden behavior; it simply provides the core function.

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, well-structured sentence. It leads with the verb and resource, includes the specific count, and mentions the features. There is no wasted wording, and it is appropriately concise for a tool with no parameters.

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?

Given the tool's simplicity (no parameters, no output schema), the description covers what an agent needs to know: what the tool returns (a list of 7 jurisdictions with privacy/legal features). It does not detail the exact structure of the returned data, but for a list operation without an output schema, this is not a critical gap. The description is complete enough for an agent to decide when to call it and to understand its 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 has zero parameters, and the schema coverage is trivially 100%. Per the guidelines, 0 params yields a baseline of 4. The description adds no parameter information because none exists, and nothing more is needed. This 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?

The description states a specific verb ('List'), a precise resource ('offshore jurisdictions ServGhost operates in'), and a specific count (7). It also mentions the included content ('privacy/legal features'). This clearly distinguishes it from sibling tools like list_plans, which presumably lists plans, making the purpose 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?

The description clearly implies when to use this tool: whenever the agent needs the list of offshore jurisdictions with their features. It does not explicitly mention alternatives or exclusions, but the context is clear enough given the sibling set. For a parameterless list tool, this level of guidance is sufficient; it would have been slightly better to explicitly state 'use list_plans for plans', but that is not necessary.

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?

With no annotations provided, the description must carry the full burden of behavioral disclosure. It states it lists plans with prices, but it does not clarify how the optional parameters (type, location) affect the output, whether it returns all plans when no filter is given, or what the response structure looks like. The availability constraints are useful, but the description leaves significant ambiguity about the tool's actual 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 two sentences with no wasted words. The core action is front-loaded, and the availability constraints are presented as a supplementary note. It is well-structured for an agent to quickly parse the tool's primary function and key restrictions.

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?

Given the tool has optional parameters and no output schema, the description should clarify how the agent should invoke it. It does not mention that type and location are filters, nor what happens if they are omitted (e.g., returns all plans across all locations). It also does not specify what fields the response will contain beyond 'prices', leaving the agent uncertain about the returned data. This is a notable gap for a simple list tool.

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?

Although the schema already documents both parameters with 100% coverage, the description adds meaningful context beyond the schema by linking plan types to location availability (e.g., GPU is unavailable in Russia due to export controls). This helps an agent understand the semantic constraints of the 'type' parameter in combination with 'location', which the schema alone does 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 states a specific verb ('List'), a clear resource ('plans'), and enumerates the plan types (VPS, dedicated, RDP, GPU) along with the key detail that prices are per location. It distinguishes itself from the sibling list_locations by explicitly mentioning plans, making the purpose 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?

The description provides availability constraints (RDP only in NL/RO/MD/RU, GPU only in IS/NL/RO/MD) that hint at when this tool would be appropriate for querying specific plan types, but it does not explicitly state when to use this tool versus alternatives or when not to use it. No sibling tool is mentioned, so guidance is implied rather than explicit.

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?

With no annotations provided, the description carries the behavioral burden. It discloses the state machine, side effects ('balance credited + bonus applied'), and the distinction between topup and legacy order lifecycles. It does not explain dry_run behavior or response format, but it gives meaningful behavioral context beyond a bare 'check status' definition.

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 efficient sentences. The purpose is front-loaded, the state transitions are compactly conveyed with arrows, and the next-step guidance is placed last without waste. 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?

The status flow and follow-up action are covered, which is the core of what an agent needs. However, with no annotations and no output schema, the description still leaves gaps around parameter roles (account_token, dry_run), polling semantics, and potential error conditions. Adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, and the description does not compensate. It implicitly ties order_id to a top-up or legacy order but adds nothing beyond the schema's existing order_id description. account_token and dry_run are not explained in the description despite low schema coverage.

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: 'Poll the status of a top-up (or legacy crypto-direct order)'. The state transitions clearly distinguish this from creation tools like topup_create and create_order, and from balance/quote tools. The purpose 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?

The description implies the tool is used after creating a top-up or legacy order, and explicitly tells the agent to call create_order after a topup confirms. It gives a clear workflow context. It does not explicitly name alternatives for polling or state when not to use it, but the intended usage is clear.

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?

No annotations are provided, so the description carries the full burden of disclosing side effects. It says 'Calculate' which suggests a read-only operation, but it never states that it does not modify state, require authentication, or have rate limits. For a tool with no annotations, this is a significant omission.

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 sentence, front-loaded with the action 'Calculate the final price', and includes all key scope elements without waste. It is concise and 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?

There is no output schema, so the description should clarify return format, but it only says 'Calculate the final price'. It also references 'disk' upgrades not present in the schema, and does not explain required vs. optional parameters or whether the call is synchronous. For a tool with 6 parameters and no output schema, this is incomplete.

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 only 33%, so the description must compensate. It mentions 'RAM / disk / extra-IP upgrades' but there is no disk parameter in the schema. It also does not explain 'type' or 'location' beyond the schema's enum. The discount context is already in the billing parameter's schema description, so the tool description adds little semantic value.

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 uses a specific verb 'Calculate' and a clear resource 'final price' with scope (plan + location + billing period). It also mentions upgrades and discounts, distinguishing it from siblings like create_order (which likely creates an order) and list_plans (which lists plans).

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 clearly implies a pricing/quote purpose, but it does not explicitly state when to use this vs. create_order or list_plans. There is no mention of 'use this to estimate cost before ordering' or 'this does not create an order', leaving usage guidance implicit.

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?

No annotations are provided, so the description carries the full behavioral burden. It does not disclose that reboot, shutdown, or reinstall can be disruptive or destructive, nor whether actions are asynchronous or require special permissions. The word 'lifecycle' hints at impact but does not explain consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with the operation front-loaded and the action list compactly appended. There is no filler or redundant content.

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 mutating tool with no annotations and no output schema, the description omits return behavior, side effects, and authentication context. It provides enough to attempt invocation but not enough to fully understand what will happen to the server.

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%, and the description does not explain account_token or server_id semantics. It only repeats the action enum already present in the schema, adding no meaningful parameter guidance.

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 uses a specific verb ('Send') and resource ('server') and enumerates all five lifecycle actions, making the tool's function immediately clear. This also distinguishes it from siblings like server_credentials or account_balance, which serve different purposes.

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 guidance on when to choose this tool over siblings, when not to use it, or any prerequisites such as server state. It names the actions but does not explain the context that should trigger each one.

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?

No annotations are provided, so the description carries the behavioral burden. The word 'Fetch' communicates that this is a read operation, and 'once status is active' adds a behavioral constraint about when it is valid. It does not discuss error behavior or the dry_run parameter, but for a simple credential-retrieval tool the transparency is adequate.

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 sentence with no filler: it states the action, the specific data returned, and the precondition. The most important information is front-loaded, and every phrase contributes meaning.

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 definition covers the basic what and when, and it enumerates the returned values (IP, root password, console URL). However, it omits operational details an agent may need, such as what dry_run does, what happens when the server is not active, and whether any authentication caveats apply beyond the supplied account_token. Adequate but with clear gaps.

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%, and the tool description explains none of the three parameters. dry_run is completely undocumented, and server_id and account_token rely on naming conventions rather than explicit semantics. The description fails 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 uses a specific verb ('Fetch') and concrete resource ('IP, root password and console URL for a server'), making the tool's purpose immediately obvious. It is clearly distinct from siblings like server_action and the billing/order tools. The 'once status is active' qualifier adds a useful condition without obscuring the core purpose.

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 phrase 'once status is active' gives an explicit precondition for using the tool: credentials should only be fetched after the server reaches active status. It does not name alternatives or exclusions, but the credential-fetching resource set is unique among siblings, so the context is clear enough for an agent to select it appropriately.

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?

With no annotations provided, the description carries the full behavioral burden. It clearly signals a read-only operation ('Return'), states that no auth is required, and establishes the intended call ordering. It does not disclose output shape, but for a simple query tool that is acceptable.

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 with no filler. The core action is front-loaded, followed by targeted usage guidance and an auth note. 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?

This is a zero-parameter, no-output-schema tool with low complexity. The description fully covers what the tool does, when to use it, and necessary preconditions. Nothing essential is missing for an agent to select and invoke it 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?

The input schema is empty, so the baseline is 4. The description adds practical context by explaining that this tool informs the amount parameter for topup_create, even though no parameters exist on this tool itself.

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 uses a specific verb ('Return') and a concrete resource ('bonus credit tiers applied to top-ups'). It also distinguishes itself from the sibling topup_create by framing the query as a precursor to that write operation.

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?

Explicit guidance is given: use this BEFORE topup_create to choose an amount that maximises free credit. This tells the agent exactly when to invoke this tool relative to an alternative, and 'No auth required' removes a potential prerequisite concern.

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?

With no annotations, the description carries the full burden. It discloses minimum/maximum amounts, automatic bonus application with interpolation rules, returned fields, and the send-from-wallet-then-poll behavior. It does not address account_token or dry_run in prose, but those are covered by the 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?

Front-loaded with purpose and limits, then bonus rules and workflow. The bonus anchor table is useful but partially redundant with the instruction to call topup_bonus first, making the description slightly longer than necessary.

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, but the description explicitly lists the returned fields (payment_id, deposit address, amount_crypto) and the exact continuation call. Combined with the schema's dry_run and account_token documentation, nothing essential 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 description coverage is 75%, so the schema already explains amount, dry_run, and account_token; crypto has an enum but is self-explanatory. The description adds no per-parameter detail beyond this, so 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: 'Top up your USD balance with crypto.' It also distinguishes itself from siblings like topup_bonus (tier lookup) and payment_status (polling) by describing the actual action and its output.

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?

Provides explicit sequencing: 'Call topup_bonus first to see the full tier table' and 'poll payment_status(order_id=payment_id) until status=confirmed.' It lacks a direct contrast with alternative creation tools like create_order, but the intended workflow is clear.

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