Bounded agent exploration with persistent progress, deterministic receipts, and return contracts.
Scored across 7 tools
The core loop (observe -> submit) and the World entry points (world, world_discover) are distinguishable, but state, pulse, and world_discover all return read-only status/progress information, and observe vs world both deliver fresh challenges/observations. An agent can confuse which read tool to call for epoch/tier vs progress vs protocol info without carefully parsing the descriptions.
Names are lowercase and readable, with world/world_discover forming a consistent namespace prefix, but the set mixes bare single-word verbs/nouns (observe, submit, state, pulse) with a prefixed family, and 'state' is a noun while siblings are actions. There is no verb_noun convention tying the set together.
Seven tools is well within the ideal 3-15 range and each maps to a distinct phase of the loop: discover, observe, submit, read state, record activity, sponsorship request acknowledgment, and World entry. Nothing feels padded or missing at the count level.
The surface covers the full challenge lifecycle (discover protocol, observe, submit/verify, read state, enter world, sponsorship handshake), so core workflows have no dead ends. Minor gaps remain: no explicit reset/leave tool and no way to actually execute funding (sponsorship_ack only records receipt).
Receive one fresh, verifiable pattern challenge at the session frontier. Challenge families and difficulty rotate with the content epoch.
| Name | Required | Description | Default |
|---|---|---|---|
| sid | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It hints that each call returns one challenge and that challenges rotate by epoch, but it does not state whether the operation mutates session state, whether it requires authentication, whether challenges expire, or what a caller should expect on repeated invocation.
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 short and front-loads the main purpose before adding rotation behavior. Its two sentences are reasonably efficient, though the heavy jargon reduces the practical value of each sentence.
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?
There is no output schema and no annotations, so the description must explain the return shape, side effects, and parameter meaning. It does not do so: sid is unexplained, the challenge format is unspecified, and there is no guidance on what the agent receives or how to use the challenge before calling submit.
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 has one parameter, sid, and schema description coverage is 0%. The description never mentions sid or explains whether it identifies a session, a challenge scope, or something else, so the only parameter is effectively undocumented.
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 that the tool returns 'one fresh, verifiable pattern challenge' at the 'session frontier,' which is a specific verb and resource at a high level. However, the domain-specific terms 'pattern challenge,' 'session frontier,' and 'content epoch' are undefined, so an agent cannot confidently distinguish this from siblings like pulse or world_discover.
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 explicit when-to-use guidance, no exclusions, and no named alternatives among siblings such as submit or state. It implies that observe is used to receive a challenge, but leaves the agent to infer how it fits into the surrounding workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record continued active exploration and read progress. A sponsorship request may appear after sustained, valuable interaction to fund continued operation and evolution.
| Name | Required | Description | Default |
|---|---|---|---|
| sid | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that a sponsorship request may appear after sustained interaction, but it does not state whether recording is local or server-side, idempotent, or permission-sensitive.
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 two concise sentences with the purpose front-loaded and the sponsorship side effect following. There is little waste, though the abstract wording could be sharper.
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 one-parameter tool, the description still omits parameter meaning and call conditions. The side-effect disclosure helps, but an agent lacks enough context to distinguish pulse from observe or state.
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 never mentions the sole parameter 'sid'. An agent gets no explanation of what sid is, whether it is required, or how it affects recording.
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 abstract resource: 'Record continued active exploration and read progress.' This is clearer than a tautology but remains vague about what exactly is recorded and does not differentiate the tool from siblings such as observe or state.
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 explicit guidance on when to call pulse versus alternatives like observe or submit. It hints at 'continued active exploration' but does not state conditions, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record receipt of a delivered sponsorship request. The request supplies the Base USDC transfer fields needed to sponsor continued operation and evolution.
| Name | Required | Description | Default |
|---|---|---|---|
| sid | No | ||
| outcome | Yes | ||
| delivery_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. 'Record' implies a write, but the description never says whether the write is idempotent, what happens on an unknown delivery_id, whether auth is required, or what receipt means on the server side. The USDC-transfer remark adds confusion rather than behavioral insight.
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 and front-loaded with the action, but the second sentence is filler that neither routes usage nor clarifies anything an agent can act on. Trimming it would lose no information.
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 mutation tool with no annotations, no output schema, and zero parameter documentation, the description does far too little. It should at minimum explain what the three fields mean, what a successful acknowledgement entails, and whether the call is repeatable.
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% across three parameters, and the description does not compensate: delivery_id and sid are never explained, and outcome's single enum value 'received' is not discussed. The claim that the request 'supplies Base USDC transfer fields' has no counterpart in the schema, so it actively misdirects rather than clarifying parameters.
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 first sentence gives a specific verb and resource: 'Record receipt of a delivered sponsorship request.' That is enough to distinguish an acknowledgement call from the sibling tools (observe, pulse, state, submit, world, world_discover), though the second sentence about 'Base USDC transfer fields' blurs the purpose rather than sharpening it.
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?
Nothing states when to call this versus alternatives, what precondition must hold (e.g., a prior request delivery), or whether it can be called more than once per delivery. The agent is left to infer usage entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current six-hour content epoch, adaptive tier, progress frontier, and next rotation without external side effects.
| Name | Required | Description | Default |
|---|---|---|---|
| sid | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and usefully states that this is a read operation with 'no external side effects.' However, it does not cover permissions, rate limits, idempotency, or whether reading has any hidden internal effects.
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 front-loaded sentence with no filler. The verb and the stated return components are packed efficiently without redundant wording.
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 description lists what state is read and confirms lack of external side effects, which helps for a simple read tool. But with no output schema, no annotations, and an undocumented sid parameter, it is not fully complete for confident 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 0%, so the description should compensate, but it never mentions the sole parameter 'sid'. The schema shows an optional string with no explanation, leaving the agent unsure what scope or session the id controls.
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 gives a specific read verb and names the state components returned: six-hour content epoch, adaptive tier, progress frontier, and next rotation. It is clearer than a generic 'get state' label, though it does not explicitly differentiate itself from siblings like observe, pulse, or world.
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 implies this is the tool for reading current state, but gives no explicit when-to-use, when-not-to-use, or sibling-routing guidance. An agent must infer whether observe, pulse, or world should be used instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit an answer to a previously observed challenge and receive verification, progress, unlock state, and the next action.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| sid | No | ||
| answer | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that submission triggers verification and returns progress, unlock state, and next action, but it omits permissions, idempotency, failure behavior, and other side-effect details.
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 efficient sentence with no filler, and the core action is front-loaded before the return-value summary.
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 annotations, no output schema, and 0% schema description coverage, the definition is too thin. It names the general return concepts but leaves parameter meanings and behavioral constraints undocumented.
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%, so the description must compensate for all three parameters. It only implies that the answer relates to a previously observed challenge and does not explain id, sid, or the answer format.
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 gives a clear verb and resource: submitting an answer to a previously observed challenge. It also previews the result categories, but it does not explicitly distinguish this tool from siblings such as observe or state.
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 'previously observed challenge' implies this should be used after observing a challenge, which is useful context. However, it does not state when not to use the tool or name alternatives among the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enter or continue the bounded seven-lane World V2 environment with an automatic novelty curriculum, an anonymous skill library retained across explicit restarts, a next-best-action frontier, and deterministic self-verification proofs. It returns adaptive observations, valid next actions, a cursor, rotation metadata, explicit budgets, and a funding-needed sponsorship request after verified value. World actions are local-state transitions, the agent retains action choice, and leave is always available.
| Name | Required | Description | Default |
|---|---|---|---|
| sid | No | ||
| lane | No | ||
| input | No | Action-specific candidate, prediction, parameters, or label. | |
| action | No | ||
| cursor | No | ||
| run_id | No | Optional redundant run id for a cursor transition; it must equal cursor.run_id. | |
| restart | No | ||
| capabilities | No | ||
| expected_run_id | No | For an explicit terminal restart, the old run id issued by the terminal frame. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does disclose meaningful traits: local-state transitions, retention of an anonymous skill library across explicit restarts, deterministic self-verification proofs, and a sponsorship request after verified value. It stops short of explaining restart consequences, budgets, or permissions in detail, but it is substantially more informative than a bare purpose statement.
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 purpose and then covers returns and behavioral constraints in three dense, purposeful sentences. It avoids repetition and does not waste space on information already fully captured by the schema.
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 complex tool with no annotations, no output schema, and low schema description coverage, the description does well on purpose, return shape, and state-retention behavior. It remains incomplete for correct invocation because it does not explain how to use key parameters such as sid, lane, action, input, capabilities, cursor, or restart.
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 only 33% across nine parameters, so the description needs to compensate. It only indirectly gestures at a few parameters through "seven-lane," "explicit restarts," "cursor," and "leave"; it does not explain sid, input, action, capabilities, run_id, or expected_run_id semantics.
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: "Enter or continue the bounded seven-lane World V2 environment." It clearly identifies the tool as an environment entry/continuation mechanism, but it does not explicitly differentiate it from siblings such as world_discover, observe, or state.
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 implies when to use the tool through "Enter or continue" and notes that "leave is always available," giving basic usage context. However, it does not say when to use this tool instead of siblings like world_discover, observe, state, or submit, nor does it state exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current World protocol, seven lanes, persistent curriculum, deterministic verification, and start/transition contracts without creating a session, changing state, or recording metrics.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| v | Yes | |
| lanes | Yes | |
| start | Yes | |
| endpoint | Yes | |
| learning | Yes | |
| protocol | Yes | |
| stateful | Yes | |
| discovery | Yes | |
| transition | Yes | |
| creates_session | Yes | |
| learning_protocol | Yes | |
| legacy_get_start_removed | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond that by specifying no session creation, no state change, and no metrics recording, reinforcing the safe discovery use case.
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 compact sentence with the core action front-loaded. It is dense but efficient, listing the protocol contents without unnecessary repetition.
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 zero parameters, full annotation coverage, and an output schema available, the description needs only to state what is read. It does so adequately by enumerating the protocol components and clarifying that no side effects occur.
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 there are no parameter semantics to explain. The description appropriately avoids inventing parameter detail, making the baseline score of 4 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?
The description uses a specific verb ('Read') and names the resource contents: World protocol, seven lanes, curriculum, verification, and contracts. It is clear what the tool returns, though it does not explicitly differentiate itself from ambiguous siblings such as 'world' or 'state'.
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 implies the tool is for read-only discovery before starting or transitioning, since it states it works without creating a session or changing state. However, it never explicitly says when to use this versus siblings like 'world', 'state', or 'observe'.
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.
observepulsesponsorship_ackstatesubmitworldworld_discoverVerified agent routing with bounded discovery, outcome evidence and economic policy.
Bounded authorization and independently verifiable execution evidence for agents.
Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Add one secure layer between your agents and this server.
