Manta Signal Gate

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

With no annotations, the description carries the full burden and does disclose the cursor/polling mechanism and a freshness constraint on age_seconds. It says nothing about token expiry, rate limits, error behavior, or what happens if the cursor is stale — significant gaps for a token-gated polling endpoint.

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 the continuation rule is present, but the opening is a sentence fragment and the three clauses are loosely strung together, making it cryptic rather than cleanly 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 3-parameter tool with no output schema and no annotations, the description covers the token source, cursor pagination, and a freshness rule, which is a reasonable core. It still omits return shape beyond 'events with ids', 'limit' behavior, and failure modes, so it is adequate but incomplete.

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 only 33% (only 'token' is documented), so the description must compensate. It usefully defines 'after' as the returned cursor for continuation, which is genuine added meaning, but 'limit' is left undocumented in both the schema and the description.

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 conveys that this tool yields new trading events carrying ids, tied to a follow token from subscribe_follow, so the resource is identifiable. However, it is written as fragments with no explicit verb ('With a follow token...'), leaving the action ambiguous — it reads partly as a description of the output rather than the operation.

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 gives real procedural guidance: obtain the token from subscribe_follow, pass the returned cursor as 'after' to continue, and act only on events with small age_seconds. It stops short of naming alternatives or stating when this is preferable to siblings like follow_state or get_history, so usage is implied rather than fully routed.

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 and no output schema, the description carries the full behavioral burden, yet it discloses almost nothing: not that this is a read-only snapshot, not whether the token expires, not the shape of the returned positions, and not whether calling it mutates server state. Only the token's provenance is explained.

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 very short, but it is two fragments rather than coherent sentences, and the purpose clause trails the token-sourcing clause instead of being front-loaded. Nothing is wasted, but the structure is sloppy enough to slow parsing.

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 single-parameter read tool with no annotations and no output schema, the description should at least say what "state" contains and that the call is non-mutating. It leaves both unstated, so an agent cannot predict the return value or the safety profile before invoking.

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?

There is one parameter with 100% schema description coverage, and the schema already states "token from subscribe_follow," so the description merely repeats it. Baseline 3 is appropriate; the description adds no length, format, or lifecycle detail about the token.

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 identifies the resource ("The bot's current positions") but is written as a sentence fragment with no verb, so the agent must infer that it fetches state. It does not distinguish itself from siblings like follow_events or get_status, which also sound like they return bot data.

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 gives a prerequisite ("a follow token from subscribe_follow") and an implied purpose ("to reconcile your own book"), which points at when to reach for it. However, it never contrasts this with follow_events or get_status, so the choice among siblings 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.

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 usefully discloses the payment mechanic and the fact that billing only occurs on success, which is real behavioral context an agent needs before calling. It stops short of auth requirements, response size, pagination, or rate limits for what is likely a large historical payload.

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 filler, and the cost signal is front-loaded so the agent cannot miss it before invoking. The ordering puts billing ahead of purpose, which is defensible given the paid nature but slightly delays what the tool actually returns.

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 and no output schema, the description is the only source of shape information, and it stays vague about what the history and 'statistics' actually contain or how large the response is. For a paid call, missing notes on volume, format, or truncation are meaningful gaps despite the adequate purpose statement.

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 no parameter meaning to add or compensate for; per the rubric this is a baseline 4. There is nothing in the description that conflicts with or obscures the empty argument object.

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 names a specific resource and scope: 'the full event history of the live bot and its statistics'. An agent can tell this is an unfiltered historical dump rather than a live stream. However, it never distinguishes itself from the sibling 'follow_events', which also concerns events, so the boundary between the two 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?

It states the cost model ('PAID via x402 ($0.25 USDC)', 'charged only on success'), which is a usage consideration, but gives no explicit when-to-use or when-not-to-use guidance relative to siblings like get_status, get_signals, or follow_events. The agent must guess when a paid full-history call is warranted over the free alternatives.

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 burden, and it does disclose two genuine traits: the data is delayed by 30 minutes and it is a subset (sample) of the full paid dataset. It says nothing about rate limits, auth requirements, or refresh behavior, so the disclosure is partial rather than rich.

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 fragments with the key differentiator ('Free') front-loaded, so it is appropriately sized and immediately scannable. The telegraphic style costs a little clarity, but nothing is wasted.

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 zero-parameter tool with no output schema, the description covers the essentials: cost, latency, and data scope. It remains thin on domain context, though, never explaining what 'positions' or 'events' mean in this API or how the sample differs in coverage from the paid feed.

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 schema semantics for the description to extend or compensate for. Nothing in the description contradicts or misrepresents the empty parameter set.

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 content clearly: open positions and recent events, offered as a free sample of paid data. It implies a read operation without naming the verb, but an agent can tell what it returns. It only weakly differentiates from siblings like get_signals or get_history, since it never says how it relates to 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?

'Free' and 'a sample of the paid data' imply this is the fallback when the paid data is unavailable or unsubscribed, which is a real usage signal. However, no alternative tool is named and no condition or exclusion tells the agent when to prefer this over get_signals or get_history.

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 burden and does well: it discloses the x402 paywall, the exact price ($0.05 USDC), where payment must be attached (_meta), that charges occur only on success, and that stale data is refused at no cost. It omits only refresh cadence and return-shape 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?

Three tight sentences. The cost/payment banner comes first, then payload, then billing and error semantics — every clause carries information an agent needs before calling.

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, yet the description enumerates the returned fields and fully explains the payment failure mode. Minor gaps remain around data freshness cadence and whether the call is strictly read-only.

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; there is no parameter surface the description needs to or fails to explain.

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?

Names the concrete payload — live open positions with entry, stop loss, take profit, last price, and 24h events — which is far more specific than the name 'get_signals' alone. It distinguishes itself from read-only history siblings by emphasizing 'live' data, though it never explicitly contrasts with get_history or get_status.

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 guidance on when to prefer this over sibling tools such as get_history or follow_events. The only conditional it states is the payment error behavior, which is a mechanic, not a use-case routing rule.

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 supplied, the description must carry the behavioral burden, and it does disclose two non-obvious traits: the cost model ("Free") relative to paid siblings and that the response reports data freshness. The small_sample flag is also a useful statistical caveat. It does not cover auth, rate limits, or whether the payload is cached, keeping it out of the top band.

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 terse sentences, front-loaded with "Free.", then the exact payload contents and the call-first directive. No filler; the parenthetical enumerates return fields 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?

No output schema exists, so the description is responsible for previewing the return, and it does list the key fields (closed trades, win rate, live days, small_sample, open book, freshness). Nothing an agent needs to call a parameterless getter is missing, though it does not describe the structure or shape of those values.

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 schema has nothing to explain and the baseline of 4 applies. The description correctly implies a no-argument call.

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 concretely what it returns: bot statistics (closed trades, win rate, live days, small_sample), an open-book summary, and data freshness. This is a specific verb+resource, though it never names or excludes the similarly-shaped siblings get_signals, get_history, or get_sample, so the agent must infer the boundary itself.

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?

"Read this before paying." gives a clear conditional for using this tool first, relative to paid siblings implied in the ecosystem. It stops short of naming any alternative tool or an explicit when-not-to-use case, so it is context without full routing.

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 burden and does well: it discloses the cost ($1.00 USDC), the payment protocol (x402), token lifetime (24 hours), and the charge-on-success-only policy. It omits failure behavior, whether repeated calls re-charge, and any wallet/auth prerequisites, but the key financial risk is stated up front.

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?

Four short sentences, each earning its place: cost/protocol first, then output, then the handoff to siblings, then the billing guarantee. The most decision-relevant fact (that it is paid) is 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?

There is no output schema, so the description correctly explains the return value (a 24-hour token) and the billing semantics. For a zero-parameter tool this is nearly complete; only failure modes and token reuse/idempotency behavior are left unspecified.

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 and the schema is empty, so there is nothing for the description to disambiguate. The baseline of 4 applies; no parameter-level information is missing or misdescribed.

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 clear this tool performs a paid subscription that issues a 24-hour token, and it names the two sibling tools (follow_events, follow_state) that consume that token, which distinguishes it from them. The core action is conveyed through the payment mechanics rather than an explicit verb+resource phrase, so it is clear but slightly indirect.

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 tells the agent what to do with the result ('Pass it to follow_events and follow_state'), which implies this must be called before those tools. There is no explicit 'use this when / do not use when' or mention of an alternative payment path, but the dependency on the two named siblings gives clear situational context.

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