Realask - verified answers from the physical world

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

With no annotations, the description carries the full burden. It explicitly states 'Read-only', 'Free', and 'safe to call repeatedly', and explains the HTTP 202 provisional behavior. No contradictions.

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 bit verbose (e.g., repeats provisional/polling concepts) but remains logically structured and easy to parse. Slightly tighter wording would be ideal.

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?

Without an output schema, the description enumerates what the response contains (facts, evidence, timestamps, confidence, freshness, limitations), and explains polling behavior. This fully equips the agent to handle 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 descriptions are detailed: both parameters come from purchase_quote, job_token is a bearer token, and it warns about non-recoverability. This adds meaningful context beyond the basic 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 clearly states the tool retrieves verification results with specific content (typed facts, evidence, timestamps, etc.) and distinguishes it from sibling tools like get_verification_status (status only) and purchase_quote (creates jobs).

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?

Provides explicit guidance on when to call (after purchase, poll until 200) and mentions the alternative get_verification_status for checking terminal state. Also explains provisional vs. final responses.

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 provided, the description fully discloses behavior: it is read-only, free, changes nothing, and safe to call repeatedly. It also describes the return object (state plus progress object) and lists all possible states. No contradictions with annotations (none exist).

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?

Although the description is long, every sentence earns its place: purpose, usage, alternatives, states, polling advice, and sibling differentiation. The critical 'Read-only' qualifier is front-loaded, and the structure flows logically from purpose to usage to alternatives.

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?

Given the tool's complexity (multiple states, polling behavior, sibling relationships) and lack of output schema, the description covers everything an agent needs: what the tool returns, when to use it, how to poll, and which sibling to use instead. Nothing essential 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% with detailed descriptions for both job_id and job_token. The tool description adds little beyond what the schema already provides, mainly reinforcing the source of the parameters (purchase_quote). Baseline 3 is appropriate because the schema carries the semantic load.

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 clearly states a specific verb ('progress check'), the resource ('a job bought with purchase_quote'), and distinguishes it from siblings by explicitly naming get_verification_result as the tool to read the answer. It also enumerates the exact states returned, leaving no ambiguity about its role.

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?

Provides explicit when-to-use and when-not-to-use guidance: 'Use this to decide WHEN to read the answer; use get_verification_result to read the answer itself' and directly suggests polling get_verification_result instead if only waiting for completion. It also recommends a polling interval (15-30 seconds).

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. It discloses key side effects: payment for a quote, starting a job, returning a job_token that is shown only once, and the possibility of a 402 response with payment requirements. This is transparent about the tool's 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 description is moderately long but efficiently packed with essential information: purpose, usage, return values, error handling, and follow-up steps. It is well-structured and not verbose, though slightly dense.

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 must explain the return values. It does so explicitly, mentioning job_id and job_token, and also covers the 402 error case. It gives enough context for the agent to know what to expect and how to handle 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?

The schema covers only 50% of parameters (idempotency_key has a description, quote_id does not). The description adds some context by referencing 'quote' and the source tools, but it does not explicitly explain what quote_id is or how it relates to the quote tools. It adds minimal value 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 clearly states the tool's purpose: it pays for a quote and starts a job. It explicitly distinguishes itself from sibling tools by calling itself 'the single purchase path' and noting there is no separate action-purchase 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?

It tells when to use the tool (to purchase a quote from either quote_real_world_answer or quote_real_world_action) and provides post-purchase steps (poll get_verification_status, read get_verification_result). It also explains the alternative path when payment capability is absent (HTTP 402), guiding the agent on how to proceed.

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 provided, the description carries the full behavioral burden. It discloses that the tool creates a real obligation, requires explicit authorization, and constrains the caller (never negotiates, pays, or substitutes). This gives agents essential insight into side effects and safety requirements, though it doesn't detail the exact response format or error conditions, which would be nice but isn't critical given the schema.

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 two sentences, front-loaded with the core purpose and action types. Every clause adds value: the obligation warning, the required fields, the constraints, and the follow-up purchase pointer. No fluff or repetition.

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?

Given the tool's complexity (13 params, 7 required, no output schema), the description covers the essential decision factors: what it does, when to use it, what's required, and what happens next. It doesn't detail every parameter, but the schema handles that at 77% coverage. The only gap is no mention of verification or status siblings, but that's not necessary for correct invocation.

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 77%, so most parameters are already described. The description adds contextual meaning by tying authorized, customer_name, customer_callback_phone, and max_price_minor to the 'real obligation' concept, and clarifies that max_price_minor is a ceiling (never negotiates). This goes beyond the schema's per-parameter descriptions, providing valuable integration context.

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 clearly states the tool's purpose: getting a free price to arrange something at a US local business, listing the four specific actions (book, hold, request_quote, cancel). It also implicitly differentiates from siblings by mentioning the follow-up purchase tool, so an agent can distinguish this from get_verification_* and purchase_quote.

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 gives clear context on when to use this tool (to get a quote before purchase) and explicitly points to purchase_quote as the next step. It also states critical usage constraints like needing explicit authorization and the caller's name/number. However, it doesn't explicitly state when NOT to use it or name alternatives beyond purchase_quote, so it lacks formal exclusions.

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 burden. It discloses that the quote is free and immutable, and specifies the returned fields. It does not detail side effects (e.g., async behavior, callback requirements) but adequately conveys the read-only nature of obtaining a quote.

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 concise sentences, front-loaded with the primary purpose and immediate actionable follow-up (purchase_quote). No wasted words; structure is clear and scannable.

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 5 parameters including a nested location object and no output schema, the description is incomplete. It does not explain how to structure the request, required fields, or the meaning of verification_mode. The agent lacks essential context to construct a correct call.

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 only 40%, and the description provides no parameter guidance. It omits explanations for location, limits, callback_url, and verification_mode beyond what the schema already offers. This forces the agent to infer parameter usage, which is insufficient given the low coverage.

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 clearly states the tool's purpose: getting a free, immutable price quote for verifying a fact about a US local business. It also lists the output fields and directs to purchase_quote, distinguishing it from the verification/action siblings.

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 explicitly tells the agent to use purchase_quote to buy the quote, which is helpful. It also implies the context (verification) differentiates from quote_real_world_action, but does not explicitly contrast all siblings or state when not to use it. This is clear enough but lacks a full exclusion list.

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