Hermes Micro-Agent

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

With no annotations, the description carries the full burden and does substantial work: it discloses the forwarding to a paid /task endpoint, the 402 failure mode, and that unimplemented tasks are refused rather than faked. That refusal semantics is valuable behavior an agent could not infer from the schema. Gaps remain around payment-hash reuse/idempotency and whether retries re-charge, which matter for a paid call.

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 critical constraint (payment required) is front-loaded in the first sentence, and the middle paragraph is only three short lines. The Args block is redundant in form but justified because the schema documents nothing. Slightly verbose ('This does NOT execute for free' restates the first line), but nothing is truly 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?

For a three-required-parameter proxy tool with no annotations and no output schema, the description covers purpose, precondition, failure modes, and parameter meaning. The one soft spot is the return value — 'the server's answer' is vague, though the shape genuinely varies per task, so a generic statement is defensible.

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 all three required parameters have no schema-level documentation, so the Args block is doing essential work. It explains that `task` must come from the `tasks` tool, that `prompt` is the text to process, and that `x_payment` is a Base transaction hash of a USDC payment — the last being a format detail the bare 'string' type would never convey. It could go further on whether the hash is single-use.

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 ('Run one paid micro-task') and adds a defining constraint ('Requires a real x402 payment first'), so the agent immediately understands this is a paid execution call rather than a discovery call. It does not explicitly name siblings like `tasks`, `price`, or `verify` as the non-paid alternatives, but the payment gate is distinctive enough to separate it from them.

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 clear: call this only after a real x402 payment, and use task names drawn from `tasks`. The description also warns that calling without payment yields 402, which effectively tells the agent when the call will fail. It stops short of routing the agent to `verify` or `price` explicitly, so exclusions are implied rather than enumerated.

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 must carry the full behavioral burden. It conveys that this is a status check and that it is free to call, which covers the essential read-only and cost profile. It does not disclose return format, auth requirements, or rate limits, leaving some behavioral gaps for a tool with zero annotation coverage.

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 wasted words; the purpose is front-loaded. The second sentence ('Free to call') is a fragment but adds meaningful behavioral context efficiently.

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 zero-parameter health check, the description is minimally adequate. It does not explain what 'status' returns (e.g., uptime, version, dependencies) and no output schema exists to compensate, so an agent lacks detail on the response shape.

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, so the baseline is 4. There are no parameter semantics to add, and the description correctly does not waste space on nonexistent inputs.

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 the resource ('Service status'), making it clear this is a health/status check. It does not explicitly contrast with siblings like execute or verify, but the purpose is distinct enough that an agent can identify it without 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?

'Free to call' signals that there is no cost barrier, which is a useful usage hint. However, there is no explicit guidance on when to use this versus alternatives, nor any exclusions or preconditions, leaving usage implied rather than stated.

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 behavioral burden. It does disclose that the call is free (no cost incurred) and that the response includes payment instructions, but says nothing about whether the quoted price is locked or expires, whether calling has any side effects, or what permissions are 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, scope stated first, no filler. 'The response is exactly what a buyer needs to pay' is slightly vague phrasing that could have conveyed the actual returned fields instead, but overall it is tight and front-loaded.

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, no-output-schema tool this is close to adequate, but the return payload is described only colloquially ('exactly what a buyer needs to pay') rather than by field, and the meaning of the sole input remains ambiguous. Those two gaps matter for an agent that must construct the call and parse 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 single parameter 'task' has 0% schema description coverage, and the description does not clarify whether it expects a task ID, a task specification, or free text. It repeats the concept ('one micro-task') without adding meaning the schema lacks, so the gap is uncompensated.

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 — 'Price one micro-task in USDC' — plus the secondary output (payment instructions), which clearly separates it from siblings like execute and verify. It stops short of naming the sibling relationship explicitly, but an agent can tell this is the quote step.

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?

'Free to call' and 'what a buyer needs to pay' imply this is the pre-payment quoting step ahead of execute, but the description never states when to call it versus alternatives or that it should precede execution. Usage is inferable rather than spelled out.

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, and it discloses the non-obvious commercial fact that this call is free and precedes payment, which is the main behavioral risk for a paid API. It does not explicitly state read-onlyness, idempotency, or output ordering, but "list" plus "free to call" conveys the safe-read nature adequately.

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, zero filler, with the purpose stated first and the usage cue second. 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?

For a no-parameter discovery tool with no output schema, the description covers what is enumerated (tasks) and the key attribute (USDC price) plus the cost model. Slightly more detail on the returned fields would help, but nothing essential to correct invocation 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 and there is no parameter meaning the description needs to compensate for. Nothing about the schema requires elaboration.

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?

"List every available micro-task and its price in USDC" gives a specific verb (list) and resource (micro-tasks) plus the payload attribute (price in USDC). It is clear enough to distinguish from siblings like execute and verify, though it never names them, so the boundary with the similarly-scoped price tool is left implicit.

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?

"Use this to see what the agent can do before paying" supplies a concrete usage context: discovery ahead of any paid call. It does not explicitly exclude alternatives or say when to use price or execute instead, so routing is guided rather than spelled out.

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 exist, so the description carries the full burden. It does disclose two non-obvious traits: the call is free and it is meant to gate a retry, which matters for a paid-endpoint workflow. It says nothing about what a failed verification does, whether errors are raised or returned as a boolean, or how quickly the on-chain lookup resolves.

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 purpose and the cost fact. Nothing is padded, though the second and third sentences could have absorbed the parameter meaning without adding length.

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 annotations and no output schema, the description must explain what verification returns and how min_cents is interpreted; it does neither. For a gating/decision tool whose whole value is a pass/fail signal, leaving the result shape unspecified is a substantive gap.

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 mentions no parameters at all. tx_hash is guessable from context (USDC payment), but min_cents with default 1000 is genuinely opaque — presumably a minimum payment threshold in cents — and the description never explains it or how it affects the pass/fail outcome.

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: "Verify a payment on-chain." The follow-on sentence about "retrying the paid request" implicitly separates it from the paid sibling (execute), so an agent can tell which one costs money and which one checks. It never names the sibling explicitly and the generic name 'verify' alone would not have carried this.

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 sequencing rule: call it after sending USDC and before retrying the paid request. That is real when-to-use guidance tied to a workflow. It offers no when-not-to-use condition (e.g., what to do if verification fails, or whether pre-payment checks are supported).

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