Omega x402 Security, Biomed & Escrow Intelligence MCP

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

With no annotations supplied, the description carries the burden and does well: it discloses that the check is a live RPC call, enumerates the outputs (risk score, verdict), and crucially warns that this is a paid x402 endpoint at $0.02 USDC with a specific GET URL. It omits failure modes (rate limits, retries, what happens on an EOA vs contract, how a low score maps to caution/avoid thresholds).

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 dense, front-loaded sentence lists the checks first and the payment/logistics parenthetical last, which is the right ordering. It is packed but each clause names a distinct check or a distinct cost fact, so little is wasted; a light bullet structure would read better.

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 output schema and no annotations, the description must convey return values, and it does enumerate the diagnostic fields plus the aggregate risk score and verdict. It is slightly incomplete on error behavior and on the cost implications of repeated calls, which matter for an agent deciding whether to retry.

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?

Only one parameter exists and the schema already documents it at 100% coverage ('Base Mainnet 0x contract or wallet address'). The description reinforces the Base Mainnet chain constraint but adds no new format, checksum, or validation semantics beyond the schema, so the baseline of 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?

The description names a specific verb+resource ('contract & escrow solvency check') and enumerates exactly what is examined: bytecode size, Circle USDC balance, EIP-1967/1167 proxy detection, pause/blacklist selector scan, risk score and verdict. That enumeration alone distinguishes it from siblings like token_rug_scan or wallet_forensics, which target different networks/asset classes.

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 is only implied: it's a due-diligence check on a Base Mainnet contract, and the mention of an escrow focus plus a numeric verdict hints at a pre-interaction safety gate. There is no explicit when-to-use vs when-not, and no routing guidance against the sibling tools (e.g. when to prefer token_rug_scan or wallet_forensics).

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 at all, the description carries the full behavioral burden, and it does add real value by disclosing that the endpoint is metered ($0.03 USDC via x402) and giving the underlying HTTP route. It omits other behavior an agent needs: whether a payment header is required before the call, what happens on upstream failure, rate limits, and what the JSON payload actually contains beyond the source names.

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 tight sentences with no filler: the data payload leads, and the pricing/endpoint parenthetical follows. The only minor cost is that the endpoint URL and price are crammed into the same sentence as the content description, slightly muddying the front-loaded scope statement.

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-parameter, no-output-schema aggregation tool the description does well to enumerate the data sources, which effectively substitutes for a return-value description. It is still incomplete on operational essentials: no-required-parameter behavior, error/failure semantics, and how 'limit' interacts with three merged data sources.

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 every parameter (drug, limit, condition) is already documented with examples in the schema, and the description adds no syntax or semantics beyond that. The baseline 3 is appropriate; a notable unresolved question is why zero parameters are marked required for a drug lookup, which the description does not address.

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 the specific upstream sources (openFDA FAERS adverse-event counts and label warnings, ClinicalTrials.gov API v2 trials, ChEMBL molecule properties) and the shape of the result ('one structured JSON call'), so an agent knows exactly what data this returns. It is clearly distinguishable from every sibling (escrow, bounty, rug scan, wallet, web extract, x402 lint). It stops just short of 5 because it never frames the core operation as a verb on a resource (e.g. 'look up a compound'), relying instead on a noun phrase plus source list.

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 reach for this tool versus anything else, no prerequisites for the paid call, and no mention of what the optional 'condition' filter is good for in practice. The only contextual cue is the price/endpoint note, which is about cost, not about selection.

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 behavioral burden. It usefully discloses that this is a paid x402 endpoint costing $0.03 USDC and provides the endpoint URL, which is important context. However, it omits key behavioral details such as authentication/payment flow, rate limits, data freshness, and return 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?

The description is a single, front-loaded sentence that states the data sources first and the pricing/endpoint second. It is dense but contains no obvious filler, though the parenthetical pricing block interrupts readability.

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 that fuses two data sources and has no output schema, the description is incomplete. It does not explain the return structure, what 'solvency telemetry' includes, how GitHub bounty discovery is scoped, or how the limit parameter affects the combined 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 input schema fully documents the single 'limit' parameter with its range and default. The description adds no additional meaning about whether the limit applies to the combined feed or each data source. With 100% schema coverage, the baseline of 3 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?

The description identifies the data domains: Base escrow vault solvency telemetry and GitHub USDC/crypto bounty discovery. However, it does not clearly state the action or output form, and the 'fused' framing makes the tool's exact purpose ambiguous. It also does not distinguish itself from the sibling base_escrow_audit tool.

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 versus alternatives such as base_escrow_audit or web_extract_intel. The paid endpoint details are present, but there are no usage conditions, exclusions, or prerequisites beyond the implicit payment requirement.

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 disclose significant behavior beyond the schema: it is a live on-chain call, it aggregates external data (DexScreener LP/FDV), and critically it is a paid x402 endpoint at $0.02 USDC with the exact gateway URL. It does not disclose response shape, latency, failure modes, or what happens if payment is missing, so it stops short of full transparency.

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?

Purpose is front-loaded and no sentence is filler, but the entire definition is one long sentence built from nested parentheses that mixes chain coverage, checks performed, data sources, and billing details. A short split into purpose / coverage / cost would be far easier to parse under token pressure.

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 with no output schema and no annotations, the description should say roughly what a caller receives (scored verdict vs raw signal list) and how the payment/what the result looks like. It explains what is inspected but not what comes back, which is the main gap given no output schema exists.

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%, so both parameters are already documented with their formats (base/solana, 0x/Base58). The description adds context about what each chain is inspected for, but supplies no additional semantics about the 'optional chain override' behavior — e.g., whether chain is inferred from the address when omitted.

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+resource ('token rug-pull scanner') with the exact chains covered and the concrete signals inspected (mint/pause/blacklist/fee-trap, proxy, mintAuthority/freezeAuthority, whale concentration, LP/FDV). An agent immediately knows this is a token contract risk audit, distinguishable from sibling tools like wallet_forensics or base_escrow_audit which operate on different objects.

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 is implied by the resource ('scan a token before trusting it'), and the enumeration of checks hints at when the tool is valuable, but there is no explicit when-to-use vs when-not guidance, no mention of alternatives, and no statement of preconditions such as needing a valid token address on a supported chain.

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 behavioral burden. It does disclose the most important non-obvious trait — this is a paid x402 endpoint costing $0.01 USDC with a concrete GET URL — which is genuinely valuable context. However, it never states that the operation is read-only, says nothing about payment/auth flow requirements, data freshness, or failure behavior, so the behavioral picture is only partly covered.

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 dense, front-loaded sentence that leads with the capability and ends with the cost/endpoint in a parenthetical. Every clause carries information; the only mild cost is that the enumeration is packed tightly, but nothing is redundant.

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 tool with no output schema and no annotations, the description does the heavy lifting by listing the return payload categories and disclosing pricing. Minor gaps remain: it doesn't explain that the address is technically optional per the schema (0 required params) or what happens on a missing/invalid address.

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% and the single 'address' parameter already documents EVM 0x... and Solana Base58 formats. The description adds only the implicit point that the same address is resolved across five chains and used for counterparty expansion; no format, normalization, or validation detail is added beyond the schema.

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 verb+resource (wallet & counterparty forensics) and enumerates exactly what is returned: native + USDC balances, nonce activity, contract vs EOA detection, and burner/Sybil risk scoring. The explicit chain list (Base, Ethereum, Arbitrum, Polygon, Solana) and the 'counterparty' scope separate it from siblings like token_rug_scan and base_escrow_audit.

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?

Multi-chain scope and the specific data types make the intended use inferable, but there is no explicit when-to-use/when-not-to-use guidance and no routing against siblings such as token_rug_scan (which likely overlaps on risk scoring). Usage is 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 burden and discloses key behavior: it fetches a public HTTPS page, returns Markdown plus OpenGraph metadata, performs a live Cloudflare DoH DNS audit across A, MX, SPF, and DMARC records, and produces an authenticity/phishing-risk score. It also discloses that this is a paid x402 endpoint with a specific price and request URL, though it does not cover rate limits or error behavior.

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 essential purpose and outputs are front-loaded, and the paid-endpoint detail is properly subordinate in parentheses. It is efficient overall, though the single dense sentence packs multiple functions and the endpoint URL into one compact block.

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 explains the main return content and the paid access model, which is useful given the absence of annotations. However, with no output schema, it still leaves the exact response structure and meaning of the authenticity/phishing score unspecified, and it does not explain error or payment-failure behavior.

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 only the public-HTTPS constraint on the URL and does not add format, range, or default details beyond what the schema provides.

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 ("Fetches any public HTTPS webpage") and clearly names its combined outputs: clean LLM-ready Markdown, OpenGraph metadata, DNS audit records, and a phishing-risk score. It is distinct from all listed siblings, which cover escrow, biomedical, bounty, token, wallet, and x402 linting functions.

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 usage by describing webpage extraction and domain-authenticity scoring, but gives no explicit when-to-use guidance, no alternatives, and no when-not-to-use conditions. The only stated constraint is that the URL must be public HTTPS, which is a scope limit rather than selection guidance.

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 present, so the description carries the full behavioral burden. It does disclose two genuinely valuable traits: the tool makes outbound network probes against an arbitrary third-party endpoint, and invocation is metered ($0.01 USDC, with the payment URL given). It omits timeout behavior, rate limits, failure modes when the target is unreachable or is not an x402 endpoint, and whether it is strictly read-only against the target.

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 sentences, front-loaded with the action and the checklist of verifications, with pricing and payment endpoint confined to a trailing parenthetical where it does not obstruct the main clause. The enumeration is dense but every item names a distinct check, so little 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 one-parameter probe with no output schema, the description comes close to complete: it lists the dimensions inspected, which implicitly describes what the result reports, and it discloses cost and payment details. It falls short only on result shape (pass/fail per check vs. a report), timeouts, and error behavior for malformed targets.

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% and the single parameter already documents 'Target HTTPS x402 endpoint URL to inspect'. The description adds a meaningful constraint beyond the schema by narrowing the target to an actual x402/HTTP-402 endpoint that speaks the v1 or v2 accepts[] schema, but no further format, auth, or example guidance is given.

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 (probes) and a specific resource (x402 HTTP 402 endpoint), then enumerates exactly what is verified: PAYMENT-REQUIRED header size, v1/v2 accepts[] schema, Base/Solana asset and payTo validity, facilitator reachability, Bazaar outputSchema readiness. That is far more specific than any sibling (base_escrow_audit, token_rug_scan, wallet_forensics), though it never names a sibling to route away from, which keeps it short of a 5.

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 intended use case is strongly implied by the enumerated checks (validate an x402 endpoint before trusting or integrating it) and by the word 'any', which signals broad applicability. However there is no explicit when-to-use, when-not-to-use, or prerequisite (e.g. whether the target must be reachable from the sandbox, or whether the paid variant is required for deeper checks).

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