AGORA Omega

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 does disclose the critical behavioral trait of cost and payment mechanism ($0.02 USDC per call via x402) and hints at the response content, but omits auth requirements, rate limits, or what happens with the supplied text.

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 compact two-clause sentence that front-loads the regulatory purpose before the output scope and pricing. No padding, though the pricing clause is appended without a clear lead-in about sequencing.

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 four undocumented parameters, the description should do more. It states what the tool returns at a high level but leaves the meaning of every input unexplained, which is the main gap an agent would hit when actually invoking it.

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?

All four parameters (texte, langue, contexte, relu_par_humain) have 0% schema description coverage, and the description says nothing about any of them — not even that texte is the input under review or what langue/contexte control. The description does not compensate for the total gap in input documentation.

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 and resource: an 'EU AI Act art. 50 transparency check' that determines whether AI disclosure is required, whether it is present, and supplies the disclosure text plus machine-readable metadata. The purpose is precise and clearly distinct from catalog/search/audit siblings, though it never names a sibling to contrast with.

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 the compliance context (EU AI Act art. 50) but gives no explicit when-to-use guidance, no prerequisites, and no alternatives or exclusions. An agent has to infer the triggering situation entirely from the purpose sentence.

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 burden. It does add real behavioral context beyond the schema: the call is free, and payment for the listed tools is in USDC via x402. It does not state that the operation is read-only/no-side-effect, nor describe the shape or volume of the returned catalog.

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 tight sentence with the most decision-relevant fact ('Free.') front-loaded. No filler and nothing restated from the name.

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 no-parameter, no-output-schema catalog tool the description covers what the tool returns and the cost/payment model, which is what an agent needs to select it. Minor gaps remain: no mention of networks covered or 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?

The tool takes zero parameters and schema coverage is 100%, so there is nothing for the description to disambiguate. Baseline 4 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?

States a specific verb ('Lists') and resource ('AGORA Omega paid tools, prices and networks'), which is clearly distinct from the check/audit/verify siblings. It does not explicitly name a sibling to contrast with, but the catalog role is unambiguous.

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?

Implied usage: call this to discover what paid tools and networks exist and what they cost. There is no explicit when-to-use vs alternatives guidance, and no statement of prerequisites, though for a zero-argument discovery tool this is largely self-evident.

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 add one genuinely useful behavioral fact not present in the schema: the per-call cost ($0.004 USDC via x402). It still omits result volume behavior, whether the call is billable on failure, and any auth/payment flow details beyond naming the protocol.

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, and the data-source/field list is front-loaded ahead of the pricing note. It is efficient, though the pricing sentence reads as an aside rather than part of a coherent usage picture.

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 four-parameter tool with no annotations and no output schema, the enumerated return fields partly compensate for the missing output schema. But the absence of any usage guidance or explanation of how q, naf, limite and departement interact leaves the definition only minimally complete.

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 the four parameters (q, naf, limite, departement) are already documented in the schema. The description adds no filtering syntax, combination rules, or default behavior beyond what the schema states, which is the expected baseline when the schema does the heavy lifting.

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 (official French company data from SIRENE/RNE) and enumerates returned fields, so an agent can tell what data it concerns. However, it never states the operation itself (search/lookup by name, SIREN or SIRET), so the verb is left to inference from the tool name rather than the prose.

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 use this tool versus the sibling tools (agora_counterparty_check, agora_supplier_audit, agora_verify_deliverable), nor any prerequisites or exclusions. An agent must guess whether company lookup is the right entry point for a given task.

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 non-obvious operational traits: the data sources, daily refresh cadence, and an explicit cost/payment model ($0.015 USDC per call via x402) that the agent must know before invoking. It does not state that the operation is read-only, nor describe response shape or rate limits, so it stops short of full disclosure.

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?

Front-loaded with purpose and coverage, followed by one sentence on data provenance and one on pricing. Every sentence carries information an agent needs and none 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?

The description covers sources, freshness, and cost, but with no output schema and no annotations it never says what a check returns (verdict, risk level, matched-list detail) or whether at least one of the two optional parameters is required. For a screening tool whose entire value is the result, that is a meaningful 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 both parameters are documented in the schema ('Legal or brand name', 'Website or domain'), so the baseline is 3. The description adds no syntax, format, or matching guidance for nom/site (e.g. whether one or both are needed, or how partial names are matched).

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 (check) and resource (counterparty) and enumerates the exact data sources consulted (AMF blacklists, ESMA MiCA register, EU/UN/OFAC sanctions). The 'before paying a platform or crypto provider' framing orients it toward payment-adjacent use, but it never names or contrasts with the adjacent siblings agora_pay_guard or agora_supplier_audit, leaving some overlap ambiguous.

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?

Gives a clear trigger context: run this before paying a platform or crypto provider. However, it states no exclusions, prerequisites, or alternatives, so an agent cannot tell from the description alone whether agora_pay_guard or agora_supplier_audit should be preferred in a given situation.

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 verdict vocabulary (ALLOW/REVIEW/HALT), the safest-payment-option output, an Ed25519-signed receipt for audit, and the per-call price. It omits auth requirements, latency, and behavior when a check source is unreachable, leaving minor 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?

Front-loads the core purpose, then the check list, verdict outputs, and cost. It is dense but every clause is informative and there is no filler, though the long parenthetical check list slightly burdens 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 with no output schema and no annotations, the description covers return values, the signing mechanism, and the usage cost, and the nested policy object is schema-documented. Only auth/prerequisite details and degraded-source behavior are missing.

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 the schema already documents url, method, policy, and payment_required; the baseline is 3. The description reinforces what policy and payTo checks mean in context but adds no syntax or format detail 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?

States a specific verb and resource: it guards payments by checking an x402 endpoint's payment request before the agent pays. It enumerates the exact checks performed (USDC contract, network, price vs policy, payTo vs OFAC/Chainalysis, domain age, blacklists, HTTPS), which distinguishes it cleanly from the sibling audit/check 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?

Clearly states the trigger condition: call it 'before paying an x402 endpoint.' That gives explicit timing context. It does not name or exclude any sibling alternative, nor describe failure/fallback paths, so it falls short of full when/when-not 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?

With no annotations, the description carries the full behavioral burden and does well: it discloses the data source (on-chain Chainlink feed), the return payload (deviation in bps, 0-100 score, level, data age and staleness), and a monetization trait no schema captures — $0.01 USDC per call paid via x402. It stops short of stating whether the call is read-only in failure/error cases or what happens when the feed is stale.

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, zero waste, front-loaded with identity then payload then cost/disclaimer. Every clause carries distinct information (source, output fields, price mechanism, scope limits).

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, so the description must cover returns and cost — and it does, listing the five returned values and the x402 payment requirement. It is nearly complete for a two-param read tool; minor gaps remain around error/staleness handling and the supported network list.

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% with two clearly documented parameters (symbol, network), so the baseline is 3. The description adds no syntax, format, or enumeration detail beyond the schema — it never mentions which networks or symbols are actually supported, even though 'base, ethereum, polygon, arbitrum' is only an example in 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?

States a specific verb and resource ('Reads the Chainlink price feed on-chain and returns the deviation from 1 USD in basis points, a 0-100 score, a level'), naming the exact artifact produced. The sibling tools cover entirely unrelated domains (AI act, catalog, supplier audit), so no overlap needs disambiguation and the name plus description make its niche obvious.

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 purpose implies the use case (checking stablecoin depeg risk) but the description never says when to reach for this tool versus another, nor any prerequisite conditions such as supported networks or feed availability. The 'not investment advice, not a forecast' line sets a boundary on interpretation but is a disclaimer, not usage 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 provided, so the description carries the full behavioral burden. It does disclose genuinely useful non-schema facts: it is an orchestrated multi-source aggregation, it returns a decision with a confidence score, and it costs $0.10 USDC per call via x402. It says nothing about latency, rate limits, caching, failure modes, or what happens when a source is unavailable — significant gaps for a paid, multi-source call 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?

Three tight clauses: what it does and which sources, when to run it, and what it costs. The purpose and the data sources are front-loaded, and every clause carries information an agent needs; there is 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?

With no output schema, the description sensibly summarizes the return as a pay/verify/do-not-pay decision with a confidence score, and it discloses the payment requirement and cost. Parameters are fully covered by the schema. The remaining gap is operational behavior (timing, partial-source failure) which is not addressed.

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 the schema already documents all four parameters (nom, site, siren, langue). The description adds no parameter-level meaning such as which identifiers are mutually exclusive or how 'langue' affects the verdict, so the 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?

The description states a specific verb+resource ('Supplier due-diligence mission') and enumerates the concrete data sources it orchestrates (French registry, AMF, ESMA MiCA, EU/UN/OFAC), plus the shape of the result (pay/verify/do-not-pay with confidence score). It is clear on what it does, but it never names or distinguishes itself from close siblings like agora_counterparty_check or agora_pay_guard, so an agent must infer the boundary.

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?

'Run it before paying a supplier or platform' gives an explicit trigger condition, which is real usage context. However, it offers no when-not guidance and does not point to the alternative siblings (counterparty_check, pay_guard) that overlap in intent, leaving the agent to guess which of the several checks to call.

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 material behavior: it is an independent verifier agent, it returns a score, doubtful claims, and a verdict, and each call costs $0.03 USDC via x402. It doesn't say whether the charge applies on failure, or comment on latency/limits, but the pricing and output disclosure is substantial context an agent needs before invoking.

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: purpose plus outputs first, the usage trigger second, and cost/payment last. No sentence is redundant and the most decision-relevant information 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, and the description compensates by enumerating the return payload (score, doubtful claims, verdict) and the payment mechanism. Parameters are fully covered by the schema. The remaining gap is failure/limitation behavior, which is minor for a 3-parameter verification tool.

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 texte, langue, and consigne are already documented in the schema, including the 12,000-char limit and fr/en options. The description adds no parameter-level meaning beyond that, so the 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?

States a specific verb (verify/check) and resource (another agent's deliverable) and additionally names the returned artifacts — quality score 0-100, doubtful claims, and a valider/corriger/rejeter verdict. The purpose is immediately legible; it just doesn't explicitly differentiate itself from the agora_* siblings by name.

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?

"Check another agent's work before paying for it" gives a concrete when-to-use trigger, which is more than most definitions offer. It stops short of stating exclusions or naming an alternative sibling for adjacent checking needs, so it falls just under a 5.

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