ogfetch

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

Annotations already flag this as a non-idempotent write with open-world effects, and the description adds meaningful detail beyond them: an external Stripe payment step, the guarantee that "Credits are added automatically after payment," and exactly what the call returns. It stops short of saying whether repeat calls create multiple independent checkout links, which matters given idempotentHint=false.

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, front-loaded with the action, then pricing, then what to do with the result, then the post-payment effect. Nothing is redundant or padded.

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 tool with no output schema, the description covers what is produced (checkout_url), how to deliver it, and what happens after payment, which is what an agent needs to complete the workflow. The one omission is disambiguation from the USDC sibling.

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 by mapping each enum value to concrete value: starter = 1000 credits/$3, pro = 5000/$10, business = 15000/$20. That lets an agent choose a plan without extra lookups; only the api_key parameter is left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: "Create a Stripe checkout link to top up this API key." The mention of Stripe implicitly separates it from the sibling buy_credits_usdc, so an agent can tell which credit-purchase tool applies.

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 explains what to do with the result ("Give the returned checkout_url to your user to pay (or complete it if you can make payments)"), which is real usage guidance for the post-call step. However, it never states when to prefer this over buy_credits_usdc or get_pricing, and gives no prerequisites beyond the optional API key.

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=false, openWorldHint=false and idempotentHint=false, and the description is consistent with all three: it creates a quote (a write-ish action) rather than charging, and repeated calls would yield fresh quotes. Beyond the annotations it adds real value — the exact response fields, the two-step POST/sign handoff, and the note that no browser is required. It omits quote expiry, whether creating the quote reserves or charges anything, and failure modes, which keeps it below 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?

Content is front-loaded — purpose first, then return fields, then the two invocation paths, then the mandatory follow-up. Every sentence carries operational information, including the inline POST body example. It is dense and slightly run-on (the JSON snippet interrupt mid-paragraph), but nothing is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly enumerates the returned fields (transaction_url, solana_pay_url, amount_usdc, reference) and explains how to consume each. It also names the required next tool, check_usdc_payment, closing the loop for a multi-step flow. Only edge details — quote lifetime, what happens if the payment is never sent, and error conditions — are 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 description coverage is 100%, so both `plan` (with its starter/pro/business enum) and `api_key` are already documented in the schema. The description hints at them with 'top up' and 'this API key' but adds no format, default, or notable-value guidance beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 opening sentence gives a specific verb, resource and scope: 'Create a Solana Pay quote to top up this API key with USDC on Solana mainnet.' An agent immediately knows this is the crypto-payment top-up path. It does not, however, contrast itself with the sibling tool buy_credits, so the agent must infer which payment rail to pick from the name 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?

The description lays out a clear operational sequence: call this to get quote URLs, POST the wallet address to transaction_url and sign/send, or render solana_pay_url as a QR for Phantom, then call check_usdc_payment. It also states 'No browser needed.' What is missing is any exclusion or comparison — nothing says when to prefer this over the sibling buy_credits (e.g. card vs USDC).

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 a mutating, idempotent, open-world operation; the description adds real value by explaining what the mutation is (credits are added once, matching idempotentHint) and what the on-chain lookup does. It also enumerates the possible outcomes (pending, credited, expired), though it says nothing about failure or error behavior when a payment is never found.

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, front-loaded with the purpose, followed by mechanism, return values, and polling advice. Every sentence adds information and nothing 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 one-parameter tool with no output schema, the description covers the prerequisite (a buy_credits_usdc reference), the side effect, the return statuses, and the polling pattern an agent needs to drive the flow to completion.

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% and the single parameter is already documented as 'The reference from buy_credits_usdc.' The description's 'by its reference' restates rather than extends that, 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 (check a buy_credits_usdc quote by reference) plus the side effect (finds the payment on-chain and adds the credits once), and names the sibling that produces the reference, so it is distinguishable from buy_credits_usdc and the other 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?

Gives concrete invocation guidance — poll every few seconds after paying — which tells the agent both when to call and the cadence. It stops short of stating an explicit when-not condition (e.g., do not poll before sending the transfer), so it is clear but not exhaustive.

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 only establish that this is a non-idempotent write with no open-world access. The description goes well beyond that by disclosing the return value (API key plus free trial credits), the irreversibility of the key ("cannot be shown again"), and that no email or browser is needed.

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, each carrying a distinct fact: what it does, the precondition, and the handling obligation for the returned key. No filler, and the precondition is front-loaded before the storage instruction.

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 correctly explains what comes back and warns that the key is unrecoverable. The one missing detail is how the key is subsequently supplied on other calls, but for a two-optional-parameter creation tool this is close to 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 100% and both parameters are marked optional with their own descriptions, so the schema already carries the semantics. The description adds nothing about name or contact, which is acceptable at full coverage but is the baseline rather than added 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?

States a specific verb and resource ("Create a new ogfetch account") plus the concrete output (an API key with free trial credits). The creation framing clearly separates it from sibling get_account, which reads an existing account.

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 precondition: "Only call this if you do not already have a key." That is a real when-to-use rule, though it does not name get_account as the alternative path for agents that already hold a key.

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 readOnlyHint/openWorldHint annotations, it discloses the billing model ("1 credit per successful fetch", implying failures are not charged) and the content of the response, including HTTP status and response time. It does not cover failure modes, redirect handling, non-HTML content, or JS-rendered pages.

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 verb first and the return payload enumerated afterward. The long parenthetical lists are dense but earn their place given there is no output schema, though they could be grouped more compactly.

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 only two parameters, the description carries the return-value burden well by naming every metadata category returned. The main remaining gap is error/edge-case behavior (non-200 responses, non-HTML pages, timeouts) that an agent would want before calling.

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

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

Schema description coverage is 100%, so both parameters are already fully documented, including the api_key optionality. The description adds no parameter-level meaning beyond the schema, which sets the baseline at 3.

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 ("Fetch a web page and return its metadata as JSON") and then enumerates the exact field families returned. Siblings are all billing/account tools (buy_credits, get_account), so the domain separation is self-evident without explicit sibling naming.

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 resource itself and the credit-cost line hints this is a metered call, but there is no explicit when-to-use / when-not guidance and no mention of alternatives (e.g. when a plain fetch or a scrape tool would be better).

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 as a read-only, closed-world operation, and the description is consistent with that. It adds little beyond the annotations and does not mention auth behavior, rate limits, or response shape, so this is minimally adequate rather than 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?

The description is a single, front-loaded sentence with no unnecessary wording. It clearly states the returned information and the subject scope without padding.

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 read-only tool with one optional, fully documented parameter and useful safety annotations, the description is largely complete. It covers the returned balance and usage, though it does not describe the response format in any detail.

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%, and the single api_key parameter is fully described in the schema, including that it is optional when an Authorization header is configured. The description adds no parameter meaning beyond that, 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?

The description uses a specific verb and resource: return the remaining credit balance and usage for the API key. It is clear what the tool retrieves, but it does not explicitly distinguish itself from siblings such as get_pricing or buy_credits.

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 states what the tool returns but gives no guidance on when to use it versus alternatives such as get_pricing, check_usdc_payment, or buy_credits. Usage is only implied by the purpose, with no explicit exclusions or routing 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 cover the safety profile (readOnlyHint=true, openWorldHint=false), so the remaining burden on the description is light. "No API key needed" is a genuinely useful addition beyond the structured fields: it tells the agent this call works unauthenticated, which matters for bootstrapping flows alongside create_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?

Two short sentences, both load-bearing, with the core action front-loaded and the auth caveat appended. No filler or redundant restatement of the title.

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 tool with no output schema and annotations carrying the safety profile, the definition is nearly complete. The only real gap is that it doesn't say what currency or format prices come in, which matters given the USDC-payment siblings.

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. Baseline 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 verb and resource: lists one-time credit packs and their prices. That is clearly distinguishable from the purchase siblings (buy_credits, buy_credits_usdc), though it never names them explicitly, so differentiation is inferential rather than stated.

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 listing/purchase split implies this is the discovery step before buy_credits or buy_credits_usdc, but the description never says when to use it or when to reach for a sibling. Usage is only implied by the read-only phrasing.

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