Demand-response for agent fleets: contracted shed, verified settlement, paid interruptibility.
Scored across 8 tools
Tools target distinct resources and lifecycle stages, but there is mild overlap in the two add_* tools (actuals vs history) and the two check-like tools (attestation vs run_probe). An agent can likely distinguish them from the terse descriptions.
Most tools use verb_noun (add_actuals, open_event, register_manifest, run_probe), but 'attestation' is a bare noun, 'settle' is a bare verb, and 'capsule_resume' reads as a compound noun. The mix is readable but not a predictable pattern.
Eight tools is well within the ideal 3-15 range for a focused aggregator; each tool addresses a distinct step in the curtailment lifecycle and none appears redundant.
The surface covers registration, event opening, readiness, reporting, settlement, and resumption, forming a coherent lifecycle. Minor gaps exist for querying/list events or retrieving manifest/event status, but agents can likely work around them.
Report one actuals minute
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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, yet it discloses nothing about side effects, whether the write is idempotent, what an 'actuals minute' mutation affects, or whether it requires prior attestation/settlement steps. The word 'Report' vaguely implies a write, but nothing concrete is stated.
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 short phrase is appropriately sized for a zero-parameter tool and is front-loaded, but it is under-specified rather than genuinely concise — it earns its brevity by simply saying very little.
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, no output schema, and no parameter documentation, the description is the only source of meaning, and a four-word phrase leaves an agent unable to tell what the tool does operationally or when to invoke it among seven 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 schema declares zero parameters, so per the rubric this is a baseline 4; there is no parameter semantics for the description to clarify or omit.
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 largely restates the name: 'add_actuals' becomes 'Report one actuals minute'. It does add the cardinality ('one') and swaps the verb to 'report', but the domain term 'actuals minute' is never explained, and it is indistinguishable from siblings like add_history, open_event, or register_manifest.
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?
There is no statement of when this tool applies versus add_history, open_event, settle, or the other siblings, and no prerequisites or exclusions are given. An agent has only the tool name to infer context, which is not enough in a domain-specific toolset.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a pre-registration meter history window
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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. 'Submit' implies a write, but there is no disclosure of prerequisites, whether the submission is idempotent, whether it can be amended or reversed, or what pre-registration state is required first.
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 no filler or redundancy. It is efficient, though the terseness comes at the cost of the specificity the agent actually needs.
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, no output schema, and no parameters, the description is the only source of meaning, and it does not explain what a 'pre-registration meter history window' contains, what state it produces, or how it relates to the surrounding settlement/attestation tools. For a mutation in a complex domain, this leaves the agent materially under-informed.
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 declares zero parameters, so there is nothing for the description to disambiguate. Per the baseline rule for parameterless tools, a 4 is appropriate; the description adds no parameter detail because none exists to add.
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 pairs a verb ('Submit') with a resource ('pre-registration meter history window'), so the general action is identifiable. However, the resource is domain jargon that is never unpacked, and nothing distinguishes it from siblings like add_actuals or register_manifest, which likely accept comparable inputs.
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?
There is no statement of when this tool should be used, when it should not, or which sibling to prefer for a related task. With seven sibling tools in an evidently stateful domain, the agent is left to guess at routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Curtailment-state check ($0.001/check x402 or manifest plan)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses a cost model and payment options, but not whether the operation is read-only, what side effects occur, what auth is required, or what the response looks like.
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 definition is a single concise phrase with the main purpose front-loaded. The pricing parenthetical is compact, though slightly cryptic without more context.
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, no output schema, and zero parameters, the description should explain what the check evaluates and what the result indicates. It does neither, leaving the agent unable to understand the tool's outcome or usage conditions.
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 are no parameter semantics to explain. The baseline for a zero-parameter tool is 4.
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 phrase "Curtailment-state check" names a verb and a domain object, but it does not explain what curtailment state means or how this tool differs from siblings. It is more specific than a tautology but remains vague enough that an agent cannot confidently select it without additional context.
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 when-to-use guidance, no prerequisites, and no alternatives among the sibling tools. The only additional information is pricing/payment detail, which does not help an agent decide when this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resume by capsule revalidation
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It hints at a mechanism ("revalidation") but omits whether this is a mutation, what state it restores, whether it requires prior context/permissions, or how failure is handled.
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?
It is short, but shortness here reflects under-specification rather than disciplined concision. A single jargon phrase that an agent cannot act on does not earn 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 tool with no parameters, no annotations, and no output schema, the description is nearly all the agent has, and it conveys almost nothing about effect or result. The void left by missing annotations is not filled.
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 declares zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool is 4. No parameter detail is missing or required.
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?
"Resume by capsule revalidation" restates the tool name (capsule_resume) with jargon rather than explaining the resource being resumed or what a "capsule" is. It does not distinguish this tool from any sibling (add_actuals, settle, attestation), so an agent cannot tell what it actually operates on.
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?
No when-to-use guidance, no preconditions, and no mention of alternatives among the sibling tools. The agent is left to infer the trigger condition entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open a curtailment event
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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, yet it discloses nothing about side effects, reversibility, permissions, or what 'opening' an event actually changes. For a state-mutating operation this is a significant gap.
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 short sentence with no waste and the verb front-loaded, though it is arguably under-specified rather than optimally concise.
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, no output schema, and an implied state change, the agent is missing everything about prerequisites, effects, and result. Zero parameters keeps the burden low, but the description still falls well short of complete for a mutating operation.
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 document and the schema imposes no ambiguity. Baseline of 4 applies with no parameter-level additions needed.
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 verb ('Open') and a resource ('curtailment event'), which is more than a tautology, but 'curtailment event' is domain jargon and nothing distinguishes it from siblings like settle or add_actuals. An agent gets the gist but no scope detail.
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?
There is no indication of when to open a curtailment event versus taking another action, no prerequisites, and no mention of any sibling tool as an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Register a task class shed contract
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it discloses nothing: no idempotency, no auth requirements, no side effects, no indication of whether registration is permanent or reversible. 'Register' weakly implies a write, but nothing confirms it.
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?
It is a single short sentence, but that is under-specification rather than conciseness — the brevity comes at the cost of any usable meaning. There is no structure to front-load because there is no 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?
The tool has no parameters, no output schema, and no annotations, so the description is the only source of meaning — and it is unintelligible jargon. Even in a sparse tool, an agent needs to know what a 'task class shed contract' is and what registering it accomplishes.
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 per the rubric the baseline is 4; there are no parameter semantics the description could add or omit.
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 pairs a verb ('Register') with a noun phrase that is domain jargon ('task class shed contract') and never explains what is actually being registered or what a 'shed contract' is. It does not distinguish this tool from siblings like add_actuals, attestation, or settle, nor can an agent tell what the operation produces.
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?
There is no when-to-use guidance, no preconditions, and no mention of any of the seven sibling tools. An agent has no basis for choosing register_manifest over attestation or settle.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a readiness probe
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 reveals nothing about side effects, idempotency, permissions, expected output, or whether the probe is safe to run repeatedly.
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 single sentence is front-loaded with no wasted words, but it is under-specified rather than appropriately concise. It leaves essential information about the tool's behavior and scope unstated.
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 zero parameters, no output schema, and no annotations, the description is the only source of context and it is nearly empty. It does not explain what 'readiness' means, what the probe checks, or what a caller gets back.
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 are no parameter semantics to document. This is the baseline score for a no-parameter 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 verb and object ('Run a readiness probe'), but 'readiness probe' is vague and does not specify what system, component, or condition is being probed. It does not differentiate this tool from any sibling, though the siblings are in unrelated domains.
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?
There is no guidance on when to use this tool, when not to use it, or what alternatives exist. The description gives no context beyond the action itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Settle an event (two-part, 15% share; replay refused)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that settlement is two-part, involves a 15% share, and that replay is refused (idempotency), which is useful. But it omits permissions, side effects, reversibility, and the meaning of '15% share', leaving significant gaps.
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 single sentence is front-loaded with the core action and contains no filler. The parenthetical is dense and slightly cryptic, but it is 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?
For a tool whose behavior is complex enough to involve two-phase settlement, a share mechanism, and replay refusal, the description is far too brief. With no annotations and no output schema, it should explain prerequisites, side effects, and expected outcomes, but it does not.
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 an empty input schema, so there is nothing for the description to clarify. Per the baseline rule for 0 params, a 4 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 ('Settle') and resource ('event'), making the basic action clear. However, it does not differentiate from sibling tools such as 'open_event', leaving the agent to infer the lifecycle relationship.
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?
There is no explicit when-to-use guidance, no prerequisites, and no named alternatives. The parenthetical 'two-part, 15% share; replay refused' describes behavior but does not help an agent decide when to select this tool over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
add_actualsadd_historyattestationcapsule_resumeopen_eventregister_manifestrun_probesettleEU power dispatch for wallet-enabled compute, DePIN, battery and trading agents.
Multi-agent settlement and clearing with validator consensus
Verified agent routing with bounded discovery, outcome evidence and economic policy.
PJM/MISO energy arbitrage. Intel TDX attested, on-chain every 60 min. MCP tools for AI agents.
Add one secure layer between your agents and this server.
