Agentgates Compute

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, and the description adds substantial context beyond that: live prices, 402 payment per network, polling behavior, renewal payment rules, owner-call signing details, control operations, and interpretation of lost answers or refusals. This is rich behavioral disclosure with no contradiction.

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 front-loaded with the core action and then enumerates the document contents efficiently. It is dense but every clause is relevant; the single long sentence is slightly packed but not wasteful.

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 that annotations cover safety traits and an output schema exists, the description provides enough detail about what the documentation contains and how an agent should use it. Nothing essential for calling this zero-parameter docs tool 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?

The tool takes zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and the empty schema is consistent with a documentation-fetching 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?

The description states a specific verb and resource: it returns Agentgates compute docs, read live as markdown. It clearly describes the document contents, but it does not explicitly distinguish this tool from siblings compute_plans and compute_quote, which may overlap with the plans/pricing material mentioned.

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 'markdown written for an agent to follow in one pass' implies this is the workflow reference to consult before buying, polling, renewing, or controlling a machine. However, it gives no explicit when-to-use guidance versus compute_plans or compute_quote, nor any when-not-to-use conditions.

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 read-only, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: data is read live from the catalog at call time (freshness), and no account, wallet or payment is required (auth/prerequisite). It says nothing about pagination or result size, but an output schema exists.

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 core purpose is front-loaded in the first sentence, followed by short operational sentences that each carry information. The opening sentence is dense and stacks several clauses (hardware, per-plan specs, hour blocks, payment network), but nothing is redundant 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 one-parameter read tool with full annotations and an output schema, the description covers what the tool returns conceptually, the payment/auth model and data freshness without needing to describe return shapes. The only meaningful omission is sibling routing relative to compute_quote.

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 `plan` parameter is already documented in the schema with the same omit-for-all semantics. The description's 'Pass `plan` to read one plan' restates the schema rather than adding format, id conventions or error behavior, so the 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?

Specific verb and resource: 'Lists the confidential virtual machines ... Agentgates rents to agents by the hour', with the per-plan fields (vCPU, memory, disk, traffic) and pricing model spelled out. It is clearly a catalog-listing tool, but it never names compute_quote or compute_docs, so the boundary with the siblings is left to inference.

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?

'Pass `plan` to read one plan' and 'Omit for every plan on sale' cover how to narrow the call, and 'Free: no account, no wallet, no payment' signals it is safe to call speculatively. However, there is no statement of when to use this versus compute_quote (the obvious listing-vs-pricing routing decision), so usage is implied rather than prescribed.

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 establish readOnly/idempotent/non-destructive, but the description adds real behavioral context beyond that: the API validates plan, hours and setup before returning an offer, so a refusal is free; the response contains one leg per network with amount in USDC, pay-to address, token, signature validity window, and signing payload. That is exactly the kind of pre-call and post-call behavior an agent needs for a payment flow.

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 the core action and tightly written, but the enumeration of offer fields and parenthetical asides make it denser than necessary; a little of the return-value detail is redundant against the output schema. Still efficient overall.

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 pricing/preflight tool in a payment workflow, it covers the mode switch, the validation-before-charge guarantee, the contents of the offer, and the handoff to the purchase path. With an output schema present and annotations covering the safety profile, nothing material 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 100%, so the schema already defines every parameter, including the machine_id-for-renewal semantics and the image/compose and plan port relationships. The description reinforces the renewal form but adds no syntax, format, or constraint detail beyond the schema; 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 verb and resource ('Gets the exact price of one machine without paying') and immediately explains the mechanism (create request with no payment → HTTP 402 offer). It also distinguishes the two modes (new machine vs. renewal via machine_id + hours), so an agent can tell exactly what this tool returns before opening the schema.

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 says when to use it (price without paying), when to switch form (pass machine_id and hours to price a renewal, payable by any wallet), and what the alternative path is (sign a leg and send the same request with X-PAYMENT to actually buy, with compute_docs as the reference). Nothing 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.