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 the call is paid ($0.20 USDC on Base) and that the four checks are bundled into one call, but says nothing about failure/billing behavior, latency, or whether results are pass/fail versus scored.

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 the trigger condition first and the capability list second; no filler. The dense jargon stack is compact rather than padded.

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 should indicate what the agent gets back — verdicts, per-check scores, or a boolean — and it does not. Given four parameters and a paid, multi-component tool, the explanation of inputs and price is adequate but the result shape is a real 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 100% and each of the four parameters is documented in-schema, including the tokenAddress example and the tradeAmountUsd purpose. The description adds only the framing that the bundle uses these inputs for the four checks, which is roughly baseline value.

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 concrete composite action: multi-oracle honeypot audit, liquidity depth, counterparty KYA, and AP2 spend-mandate checks in one call, plus its price. That distinguishes it reasonably from the single-purpose siblings (aegis_token_audit, aegis_wallet_kya), though it never names them explicitly.

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?

Starts with an explicit 'USE WHEN' trigger naming the caller (autonomous trading agent or sniper bot) and the situation (pre-swap clearance). It gives no when-not guidance or pointers to the cheaper single-purpose siblings when only one check is needed.

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 valuable traits: 100% fresh/un-cached results, multi-oracle sourcing, priority execution, and a $0.05 USDC cost on Base. It does not explain the payment/auth flow (how USDC is charged, x402-style handshake?), what happens on oracle failure or partial coverage, or latency expectations — significant gaps for a paid, priority-tier 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?

A single sentence, front-loaded with the 'USE WHEN' trigger and containing no filler. It is efficient, though the trigger-only phrasing means the actual operation never appears as an explicit predicate.

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 should say what the audit returns (score, oracle verdicts, risk flags, freshness timestamp) — it does not. For a paid, high-stakes security tool, the missing return-shape and failure semantics leave an agent unable to reason about the result it will get for its $0.05.

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% (address and chain with an enum and default of 'base'), so the schema already documents both parameters and the baseline of 3 applies. The description adds no parameter-level meaning beyond noting the payment/execution context is Base, which does not clarify how 'chain' behaves relative to the Base-denominated fee.

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 modality: a fresh, un-cached, multi-oracle token security audit with priority execution, priced at $0.05 USDC on Base. That distinguishes it from the sibling aegis_token_audit (presumably cached/standard) and aegis_recent_audits without opening either schema. It is framed entirely as a 'USE WHEN' condition rather than an action statement, which slightly blunts the verb.

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 clear triggering context (sniper bot or HFT agent needing un-cached, priority results), which is more than most tools offer. However, it never says when NOT to use it or names the cheaper alternative (aegis_token_audit / aegis_token_preview) that an agent should pick when freshness and priority are not required — the single most important routing decision for this family.

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 useful traits: the tool is free and covers three specific chains. It says nothing about return shape, streaming vs. snapshot semantics, refresh cadence, or rate limits.

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 zero filler, with the trigger condition placed first. It is efficient but so terse that it verges on under-specified for a monitoring tool.

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 and no annotations exist, so the description is the only source of behavioral and return-value information, yet it never says what a 'recent audit' contains (token address, risk score, timestamp). For a streamed-list tool an agent would need that to use the results correctly.

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?

Zero parameters, so there is nothing for the description to disambiguate; per the baseline for 0-param tools this sits at the schema's default. The chain list in the description is scope, not a filter parameter, so it adds no parameter-level meaning.

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 resource and scope: a real-time stream of recently scanned tokens across Base, Ethereum, and Solana. It is clearly distinct from point-in-time siblings like aegis_token_audit or aegis_priority_audit, though it never names those alternatives explicitly.

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 'USE WHEN:' prefix gives an explicit trigger condition (monitoring the real-time scan stream), which is the strongest form of positive guidance. It offers no when-not guidance or pointers to the single-token audit siblings.

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 behavioral weight, and it does disclose the paid nature and price ($0.01 USDC) plus the intended pre-transaction timing. It says nothing about result shape (verdict vs. score), latency, or whether the call is read-only, which are real gaps for a no-annotation tool.

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 the trigger first and no filler. Every clause (checks performed, timing, price) 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 two-parameter tool this is close to sufficient, and the paid-call disclosure is useful context. The remaining gap is that with no output schema the description never indicates what an audit returns, so the agent cannot plan on the response format.

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% with only two params (address, chain enum), so the schema already does the semantic work. The description adds no parameter-level information, and its 'on Base' phrasing slightly conflicts with a chain enum that also allows ethereum and solana.

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 (smart contract / token) and concrete checks (security, honeypot traps, buy/sell taxes), so an agent knows exactly what the call produces information about. It falls short of 5 because it never distinguishes this from aegis_priority_audit or aegis_preflight_bundle, which likely overlap.

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 WHEN ... before executing a token swap' gives an explicit trigger and timing, which is strong usage guidance. It offers no exclusions or named alternatives for when a different audit tool is the better choice.

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 disclosure burden. It usefully states the tool is free and focused on basic market data, but it does not clarify read-only behavior, rate limits, data freshness, or response format.

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 the usage condition first and no wasted text. It is appropriately sized for a simple two-parameter read tool.

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 names the key returned data categories (market pool, price, liquidity) and the no-payment constraint. With full schema coverage and no output schema, it is nearly complete, though it could say more about output shape or limits.

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 both parameters are already documented in the schema. The description adds no syntax or formatting guidance beyond the schema's chain enum and address field.

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 clear capability: checking basic DEX market pool, price, and liquidity for any token. It distinguishes the tool as a free/basic preview, but does not explicitly contrast it with sibling audit tools.

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 'USE WHEN' phrasing gives a clear condition for invoking the tool: basic DEX market, price, and liquidity checks without payment. It does not name when to avoid it or which sibling to use for deeper audits.

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 behavioral burden. It discloses GoPlus sanctions sourcing and an apparent $0.01 USDC Base cost, but never states read-only/no state change, auth needs, rate limits, or response format, and the cost phrasing is ambiguous.

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?

One front-loaded 'USE WHEN' sentence with zero padding. Each clause contributes scope, trigger context, or cost 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 one-parameter check with no output schema or annotations, listing reputation, transaction count, balances, and sanctions flags tells the agent what comes back. It still leaves read-only status and exact response shape implicit.

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 address parameter has 100% schema description coverage, including '0x EVM wallet or agent contract address on Base.' The description's 'counterparty wallet' adds little beyond the schema, so 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?

Names a specific check and enumerates wallet reputation, transaction count, USDC/ETH balances, and sanctions flags, which separates it from token-audit and preflight siblings. It never explicitly contrasts those siblings, so the purpose is clear but not fully differentiated.

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 'USE WHEN' checking a counterparty wallet before transacting, giving a clear trigger context. It does not state when not to use it or name an alternative for token-level checks, so exclusions are absent.

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 disclosure burden. It does add real behavioral context beyond the schema: a $0.005 USDC cost on Base (a payment gate the agent must account for) and the output format (LLM Markdown). It omits rate limits, JS-rendering behavior, failure modes, and size limits, which matters 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?

A single front-loaded sentence with the trigger condition first and the cost/output details trailing. No filler.

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 the description covers purpose, trigger, output format, and cost. Only operational details like error behavior and page-size limits are absent, which are minor for this simplicity level.

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% for the single url parameter, so the baseline is already high. The description adds a constraint beyond the schema by specifying 'public URL', narrowing acceptable 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?

States a specific verb (scraping) and resource (public URL) plus the transformation (page → clean LLM Markdown). The conversion output is a meaningful differentiator against the audit-oriented siblings, though it never names them directly.

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 'USE WHEN:' prefix gives a clear triggering condition: any public URL to be scraped. There are no explicit when-not conditions or named alternatives, but for a single-purpose scrape tool the trigger is unambiguous.

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