Genko Prior Auth public docs

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 safety profile is covered. The description adds genuine context beyond that: the answer is derived 'from what the product implements' and it discloses a real limitation — a payer may be supplied but is not evaluated, and the response says so. It stops short of describing latency, auth, or failure modes, but the output schema covers the return shape.

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 with no filler; the core capability and its enumerated outcomes are front-loaded, and the payer caveat follows as a qualifying clause. Slightly awkward phrasing ('Say whether ... from what the product implements') costs it the top mark, but nothing is padded.

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 an output schema present, the description needn't spell out return values, and rich annotations cover the safety profile. It supplies the decision-relevant detail — outcome categories and the payer non-evaluation caveat — so an agent can call it correctly and interpret the answer; only explicit sibling routing 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 description coverage is 100% and both parameters are documented in the schema itself, so the baseline is 3. The description's payer remark largely restates the payer field's own schema description ('The product does not evaluate payers; the answer says so'), adding emphasis rather than new meaning, and it says nothing about specialty formatting beyond what the schema examples already give.

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 ('Say whether') and resource (Genko Prior Auth's support for a practice's specialty), and enumerates the three possible verdicts (own form, general form, not supported) plus the secondary payload ('what it offers there'). This is clearly distinguishable from the sibling documentation tools (search_docs, get_page, get_product_facts), which retrieve content rather than answer a fit question.

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 when to reach for it via the outcome it answers, and the payer clause is effectively an exclusions statement ('does not evaluate payers or payer rules'). However, it never explicitly frames when to use this instead of siblings like get_product_facts or get_payout... get_pricing, leaving routing to inference.

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 closed-world traits, so the bar is lower. The description still adds genuine scope boundaries beyond the structured data: "No patient data, no code descriptors," which preempts two plausible but wrong expectations about the payload.

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 compact sentences: content scope first, then a usage cue, then exclusions. Nothing is padded, though the inline enum re-listing slightly duplicates the schema rather than earning new information.

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 an output schema present, return values need not be explained, and annotations cover safety. For a one-parameter read-only tool the description covers purpose, content classes, and exclusions adequately; only explicit alternative-routing guidance is 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 description coverage is 100% and the single specialty enum is fully documented, so baseline is 3. The description merely restates the enum options inline (dental, aesthetics, physiotherapy, generic) without adding selection guidance the schema lacks.

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 resource (what Genko Prior Auth collects for a prior authorization request), scopes it to a specialty, and enumerates the returned content classes (request details, structured-findings fields, code systems). It is clearly distinguishable from siblings like get_pricing or search_docs. The retrieving verb is only implicit, which keeps it just 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?

It offers one usage cue, "Useful for 'what goes in a packet'," which implies the scenario but gives no explicit when-not conditions or named alternatives. Siblings are unrelated enough that no routing guidance is strictly needed, but the description leaves context to inference rather than stating it.

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, non-destructive, and closed-world. The description adds real value beyond them: the output is Markdown matching the .md rendition, and the scope is limited to public content with no signed-in app access.

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: the first delivers purpose, format, input forms, and examples; the second delivers the access boundary. Nothing is wasted and the key scoping constraint 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?

An output schema exists, so return values need no explanation, and the description covers input forms and access scope. Only minor gaps remain, such as behavior on an invalid or non-existent path.

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 the single 'path' parameter is fully documented in the schema, including pattern, length limits, and accepted forms. The description's examples ('/pricing', '/facts', '/docs/faq') largely restate what the schema already conveys, so this is baseline territory.

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 (Read), resource (one public Genko Prior Auth page), and output format (Markdown, same as its .md version), with concrete path examples. An agent can distinguish this generic page reader from more targeted siblings like get_pricing and get_product_facts.

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 usage with 'Public pages only; the signed-in app is never available,' which tells the agent when this tool applies. However, it does not name an alternative such as search_docs for when the agent does not already know a path or URL.

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 read-only, closed-world, idempotent, non-destructive behavior, so the description's main added value is the scope of data (US dollars, per practice per month) and the prohibition against estimation. It does not describe error handling or response format, but the output schema covers return values.

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 tight sentence covering the data, currency, unit, included fields, and the free trial, followed by a direct usage instruction. No fluff, front-loaded with the core resource.

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 zero parameters, a rich output schema, and clear annotations, the description is complete: it states what data is returned, the unit, and when to use it. Nothing an agent needs to call or interpret the tool 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?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and its mention of plan contents adds minor context without being redundant.

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 resource ('Current Genko Prior Auth plans') with a clear unit of measure ('in US dollars per practice per month') and names the fields returned (monthly draft, AI-token limits, free trial terms). This distinguishes it from siblings like get_product_facts and get_page, which are likely general-purpose 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?

Explicitly provides a when-to-use trigger ('Use this to answer: how much does it cost') and a clear exclusion ('never estimate prices'), directing the agent to this tool for pricing queries rather than guessing or using other sources.

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?

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond them by disclosing provenance and consistency: 'Same source as /facts and /facts.json', which tells the agent the answer is stable and citable across interfaces. It does not state anything about latency, caching, or how the content is versioned, which keeps it below 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?

One content-scope sentence, one provenance sentence, one imperative directive, with no filler. The resource identity is front-loaded and the actionable instruction ('Quote these instead of guessing') lands last, where it is most likely to be retained.

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?

An output schema exists, so the description is not obliged to explain return values, and it instead spends its budget on scope and provenance, which is the right trade. For a zero-parameter, read-only lookup the agent has everything needed to call it correctly. The only gap is the missing hand-off to overlapping siblings like get_pricing.

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, so the schema has nothing to explain and the baseline is 4. The description usefully compensates by enumerating the subject areas the returned facts cover, which tells the agent what it can and cannot expect to source here. No parameter-level detail is needed or missing.

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 concrete resource (checked facts about Genko Prior Auth) and enumerates exactly what those facts cover: what it is and isn't, who it's for, stage, specialties, payer handling, security, limits, pricing and agent support. That is far more specific than the title alone. It stops short of a 5 because it never says how it differs from siblings such as get_pricing or check_fit, which overlap on the pricing and fit topics it lists.

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?

'Quote these instead of guessing' is a real usage instruction: it tells the agent to treat this as the canonical source for factual claims rather than fabricating them. However, it offers no explicit condition for choosing this tool over get_pricing, check_fit, or search_docs, even though the description's own content list overlaps with those siblings. Usage is therefore implied rather than routed.

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 establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is low. The description adds genuinely new context: results are capped at 10 ranked pages with URL and snippet, and only public content is indexed (no practice or patient data). The result-cap detail is partly redundant with the limit parameter's maximum of 10 and the output 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?

Two sentences, both load-bearing: the first scopes what is searched, the second covers the result shape, the follow-up tool, and the data boundary. The routing advice (get_page) is front-loaded where it matters, with no filler or restated title text.

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?

An output schema exists, so return-value detail is not the description's job; it still summarizes the shape (ranked pages with URL and snippet) as a courtesy. For a two-parameter, fully-documented search tool with a clear content boundary and a named follow-up tool, 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 description coverage is 100%: both query (with examples) and limit (range, default) are fully documented in the schema. The description adds no parameter-level syntax, format, or constraint information beyond what is already there, 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?

States a specific verb (Search) and resource (Genko Prior Auth public site), then enumerates the content types covered (docs, prior auth guides, specialty pages, pricing, facts). It also distinguishes itself from the get_page sibling by naming it as the follow-up for full reads, so an agent can tell the two apart 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 routes the agent: search here, then 'read one in full with get_page,' and draws a boundary with 'Public content only, no practice or patient data.' It does not, however, say when to prefer this over other siblings like get_pricing or get_product_facts, which cover overlapping subject matter (pricing, facts) that this search also claims to index.

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