Agent Council

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 price ($0.01 USDC per call) and the return composition, and the schema pairs it with the x402 payment and free-trial mechanics. It still omits latency, error/refund behavior, and whether the three models are distinct providers, so it is not fully transparent.

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 tightly packed sentences: capability first, then the use case that selects it, then the price. No filler, and the most routing-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?

With no output schema, the description usefully enumerates what comes back (verdict, confidence, agreements, dissent, what would change the answer), which an agent needs to interpret results. The payment path is left mostly to the schema's field descriptions, and sibling differentiation is absent, keeping it short of 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 q, x_payment, and free_trial are already fully documented. The description's only extra contribution is the phrase 'quick tier only' for the free trial, hinting at a tier structure the schema does not spell out; otherwise it stays at the baseline.

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 verb and resource ('Put one question to 3 DIFFERENT AI models and get a single verdict back') and enumerates the shape of the result (confidence, agreement, dissent, counterfactual). It does not, however, distinguish itself from its siblings council_deep and council_grounded, so an agent cannot tell from the text which council variant to pick.

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 an explicit when-to-use framing with example decision questions ('is this safe, is it worth it, which option'), which is exactly the context an agent needs to route a judgement call here. It stops short of naming when NOT to use it or pointing to the deep/grounded siblings as 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 disclosure burden and does add value: it explains the two-round revise-with-visibility behavior and the $0.03 USDC price, which is real context beyond the schema. It does not state latency, how the verdict is delivered, or what happens on partial failure, so it is helpful but not exhaustive.

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 dense sentences, front-loaded with the mechanism before the usage triggers and price. Nothing is padded, though the metaphor-laden phrasing costs a little precision that a plainer sentence could have delivered.

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 paid, multi-model inference tool with no output schema and no annotations, the description covers the mechanism, the cost, and the usage context. Return shape is only implied ('the verdict', low confidence, dissent), which is adequate but leaves the agent guessing about the exact response structure.

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%, including the decision-question framing for `q` and payment semantics for `x_payment`/`free_trial`, so the baseline is 3. The description adds no parameter-level detail beyond what the schema already says.

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 mechanism: a 4-model panel over two rounds where each seat sees the others and revises, producing a 'verdict'. It positions itself relative to the `council` sibling ('the same panel', implying a deeper variant), but never distinguishes itself from `council_grounded`, so an agent has to infer which of the two deepened tiers fits.

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 explicit triggers: use when being wrong is expensive, or after a `council` call returned low confidence or real dissent. That names an alternative and the condition that selects this tool, which is strong routing guidance. The `council_grounded` alternative is left unaddressed, so the selection guidance is clear but incomplete.

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 substantial work: it names the exact evidence purchased (honeypot/owner-powers simulation, OFAC screen, page content, SEC profile, web results), the two-round/four-model argument, and the response shape. It also discloses the payment contract — an unpaid call returns an itemised quote for free, and pricing is $0.05–$0.12 per question. Missing latency, rate limits beyond the daily free call, and failure modes keeps it from a 5.

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 the core action ('Buys the FACTS first, then deliberates') and every following sentence adds distinct information — scanning logic, evidence types, deliberation structure, response contents, pricing. Slightly dense but 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?

No output schema exists, and the description compensates by stating the response lists every source and what was spent. Combined with the payment lifecycle and evidence scope, an agent has enough to invoke it correctly; only operational details like timing and rate limits are absent.

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 q, x_payment and free_trial. The description reinforces the payment flow (unpaid call yields a free quote, which is what x_payment later settles) but adds no syntax or format detail beyond the schema, 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-and-resource action: buys evidence (contract/URL/ticker), then runs a 4-model, two-round deliberation. The 'grounded' positioning and the enumerated evidence types make it distinguishable from a plain council call, though it never names the siblings council or council_deep 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?

Implied usage is clear — reach for this when the question hinges on a contract address, URL or $TICKER whose real-world evidence must be fetched. However, there is no explicit when-to-use/when-not guidance versus council or council_deep, so the agent must infer the routing from the word 'grounded'.

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