Frontera Signal

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavior the annotations cannot convey: the 4-week truncation limit, that the remainder is paid, and that each row carries week, as_of and status. It stops short of stating pagination or ordering guarantees, so it is strong 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?

Three sentences, zero filler: scope first, series enumeration second, paid-alternative routing last. The most decision-relevant constraint (4 weeks, free) is front-loaded rather than buried.

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 describing row shape (week, as_of, status). Combined with the enum explanation and the paid/free boundary, an agent has everything needed to call this correctly and to know when not to.

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 enum already lists the five values, so the baseline is 3. The description goes beyond by explaining what each value actually measures (e.g. 'permits-weekly (building permits by city)', 'labor-ranges (labor and financing conditions)'), letting an agent pick the right series without external knowledge.

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 (Get) and resource (latest 4 weeks of a weekly Rio Grande Valley series) and enumerates each available series with a parenthetical gloss of what it measures. An agent can distinguish this from get_sample and list_endpoints without opening either schema.

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 scopes the tool to the free window ('latest 4 weeks ... for free') and routes the agent elsewhere for anything older: 'The full history is a paid endpoint; how_to_pay with series-<name> gives its URL and price.' That is a clear when-to-use / when-to-use-something-else split naming the sibling tool.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely useful context the annotations lack: the response is byte-for-byte what a paid call returns, making it a faithful preview rather than a truncated teaser. It does not mention any rate limit, quota, or whether repeated samples are capped, which is the main remaining gap.

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, zero waste, and the payoff ('so you can check the fields, dates and coverage before you pay') is front-loaded alongside the core action. The parameter guidance follows naturally in the second sentence.

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 only one required enum parameter, no output schema, and annotations covering safety, the description is complete: it explains the value proposition, the fidelity of the return, and where to obtain valid endpoint keys. Nothing an agent needs to call it correctly is 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% and the enum already lists all 14 valid keys, with the schema description itself pointing at list_endpoints. The description restates the same guidance plus a few example keys, adding no syntax or format detail beyond the structured field, 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+resource (get a free sample answer from a paid endpoint) and clarifies the scope: one endpoint, returned exactly as a paid call would return it. This is clearly distinguishable from list_endpoints (which enumerates keys) and get_free_series (which is a specific series), so an agent can route without opening a schema.

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 clear when-to-use context ('check the fields, dates and coverage before you pay') and routes the agent to list_endpoints as the source of valid endpoint keys. It does not explicitly state when not to use it (e.g., after subscribing, or for bulk pulls), so it stops short of a full alternative/exclusion statement.

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?

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: it never calls the paid endpoint and never pays, it performs the same pre-payment validation the API runs, and payment is x402 with no account or API key, USDC on Base. That is exactly the extra detail annotations cannot express.

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 sentences, front-loaded with the outcome (URL, price, network, asset), then inputs, then the validation behavior, then the payment model. Nothing is redundant and no sentence is 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 2-parameter, nested-object tool with no output schema, the description explains what is returned (URL, price, network, asset), how params are validated, and the payment mechanics. An agent has everything needed to call it correctly and interpret the 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?

Schema description coverage is 100%, with the endpoint enum and the params object fully documented in the schema itself, so the baseline is 3. The description restates that you pass the endpoint key and query parameters but adds no syntax or format detail beyond what the schema already 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?

States a specific verb and resource: 'Get the exact URL to call for a paid answer, with its price, network and asset.' The 'paid' framing implicitly separates it from the free siblings (get_free_series, get_sample) without needing to name 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?

Makes the use case clear: run your planned endpoint+params here first, because they pass the same free check, so refused or empty queries surface before payment. It stops short of explicitly naming alternatives or stating when NOT to use it (e.g. 'use get_sample for a free preview'), but the context is unambiguous.

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?

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the bar is lower; the description adds cost context ('before you spend anything', 'Free') and discloses the per-entry payload contents. It does not mention auth requirements or pagination, minor gaps against an already-covered safety profile.

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, then payload contents, then cost. The long enumeration of data domains is dense but earns its place for a catalog tool; a tighter grouping could have shortened it slightly.

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 carries the return-value burden and does so fully — it lists the exact fields of every entry and confirms the call is free, giving the agent everything needed to call and consume 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?

Zero parameters, so the baseline is 4. The description usefully explains what each returned catalog entry contains (price per call in USDC, return payload, example question, parameters with valid values, sample URL), which compensates for the absent output 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?

Specific verb+resource ('List every paid Frontera Signal endpoint') with an explicit scope statement ('before you spend anything') that separates it from the free-access siblings like get_sample and how_to_pay. The enumerated data covers make the resource 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?

'before you spend anything' clearly signals the discovery/pre-purchase context, and 'Free' tells the agent this call itself costs nothing. It does not name a sibling as an alternative or state exclusions, so it falls short of a 5.

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