agproxy

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false) by disclosing that a human reads it, that there is no payment or account requirement, and that throughput is rate-limited to a few messages per hour. The 'no secrets or private data' caveat is also useful guidance the annotations do not 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 short sentences, front-loaded with the cost/effort answer ('Free.') that a caller cares about first. Every clause carries information: purpose, examples, human review, cost/auth, rate limit.

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 four-parameter write tool with no output schema, the description supplies everything needed to call it correctly — purpose, cost, auth, throughput limit, and content cautions. No material gap remains.

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 documents route, contact, and message. The description's mention of 'a bug, an idea or a thanks' loosely maps to the kind enum but adds no new meaning for route or contact, so baseline 3 applies.

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

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

States a specific action (tell the service operators what worked/failed/is missed) and enumerates the input kinds (bug, idea, thanks), which maps directly onto the tool's role. It is unmistakably distinct from the fetch and proxy 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?

Clearly signals when to use it — for bugs, ideas, or thanks — and gives concrete operational context (free, no account needed, a few messages per hour). It stops short of an explicit when-not or a named alternative, but for a terminal feedback action that is a minor omission.

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?

Goes well beyond annotations: discloses cost model (pay per MB, failures not charged, pay per call in stablecoins), the 10 MB cap, truncation flagging, and header override behavior. Annotations only cover read-only/open-world; the description adds the pricing and payload-size behavioral context an agent needs.

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 dense sentences, front-loaded with the core action and return shape, then method/headers/country, then the critical billing terms. Every clause carries load.

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?

Covers action, return shape, methods, limits, cost, and failure handling for a 6-param tool with no output schema. Minor gap: no explicit routing to the 'proxy' sibling or pagination/large-body retry guidance for a >10 MB response.

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

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

Schema coverage is 83%, so the schema documents most params. The description adds method set (GET/HEAD/POST), 'your own headers,' and 'optional country' in prose, but does not explain parameters the schema leaves undocumented or add syntax beyond it.

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 (fetch) and resource (one URL) with the differentiator that it goes through a residential IP and returns raw JSON. The sibling 'proxy' is implicitly distinguished by the 'raw response' framing, though not named explicitly.

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?

Says 'No JavaScript rendering,' which is a clear when-NOT-to-use-this signal (use a browser-rendering tool instead). However, it does not name or route to the sibling 'proxy' tool or state when to prefer one over the other.

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 declare readOnlyHint=true ('does not modify its environment'), but the description states 'Pay for gigabytes of traffic' and 'get a proxy login ... after payment', i.e. a paid purchase that transfers value and provisions a credential. That is an environment-modifying, non-read-only operation, so the description directly contradicts the annotation. The genuinely useful behavioral context it does supply (90-day expiry, stablecoin payment, Base/Polygon only, per-connection rotation) cannot offset a contradiction about whether the tool is mutating.

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?

Five short sentences, each carrying a distinct fact (who it is for, what you get, how to use it, geo/rotation, duration, payment rails), with the core purpose front-loaded. Slightly list-like and abbreviation-heavy ('90 days', 'Not offered on Solana'), but there is no filler.

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

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

With no output schema, the description usefully describes the returned artifact (a host/port/username/password login usable with any HTTP client), plus duration, geo options and accepted payment chains. What it omits is the mechanics of payment (how the stablecoin transfer is actually effected) and whether the credential is single-use — meaningful gaps for a commerce 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?

Schema description coverage is 100% – both `gb` and `country` are fully documented, including the byte counting and the per-connection username override. The description's mention of choosing a country and rotating the IP slightly amplifies `country`'s meaning, but the 'session tag' concept it introduces is not a parameter in the schema, so it adds little parameter-level information.

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 makes a generic name concrete: it states that the tool sells a residential proxy pack, charges per gigabyte, and returns a proxy login (host, port, username, password). That is a specific verb-and-resource statement an agent can act on. It does not, however, distinguish itself from the sibling `fetch`, which an agent might assume is the tool for actually routing traffic.

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 context is implied rather than explicit: 'for AI agents' and 'to use with curl, a browser or any HTTP client' tell the agent the downstream purpose, and the choice of country/rotation gives selection guidance. There is no when-not guidance and no mention of how this relates to the `fetch` or `feedback` siblings, so routing between tools is left to inference.

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