Zinvyl Fixed-Scope Marketplace

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read operation. The description adds the specific output ('acceptance tests and evidence boundaries') but does not elaborate on what 'evidence boundaries' means or any limitations. It adds some context beyond annotations but lacks depth, so a 3 is appropriate.

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 single, front-loaded sentence with no filler. It states the action, object, and scope immediately, making it easy to scan. Every word earns its place.

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 simple tool with one parameter and no output schema, the description is adequate but leaves gaps. The term 'evidence boundaries' is domain-specific and unexplained, and the agent might not know what the return structure looks like. While annotations cover safety, the description does not fully define the output's nature, so a 3 reflects the missing clarity.

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 0%, so the description must compensate by explaining the parameter. It only implies that the offer_id corresponds to a 'published offer', but does not explicitly define the parameter or its format. The enum values are cryptic and the description does not decode them. This is insufficient compensation for the total lack of schema descriptions.

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 ('Return'), resource ('acceptance tests and evidence boundaries'), and scope ('one published offer'). This distinguishes it from siblings like list_offers (listing offers) and prepare_purchase_route (routing), and the agent can immediately infer the tool's 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?

The description provides clear context: it is for a single published offer, which implies the caller must have an offer_id. However, it does not explicitly mention when to prefer this over siblings or any exclusions. Since the context is unambiguous but alternatives are not addressed, this earns a 4.

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 readOnlyHint=true, idempotentHint=true, and openWorldHint=false. The description adds genuinely useful behavioral context: there are exactly two authoritative offers, and the response includes prices, inputs, acceptance tests, exclusions, and invoice-request URLs.

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, front-loaded sentence that names the exact output and its contents with no filler. Every phrase earns its place.

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 zero-parameter, read-only, idempotent list tool with a fully described output inventory, the description is complete. 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?

The tool has zero parameters, so the baseline is 4. The description appropriately focuses on the fixed output rather than inventing parameter-level detail that does not apply.

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 ('Return'), names the exact resource ('the two authoritative fixed-scope offers'), and enumerates the included content. The title and sibling names (get_acceptance_tests, prepare_purchase_route, qualify_task) make it distinct.

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 this is the canonical source for fixed-scope offer details, but provides no explicit guidance on when to use it versus siblings such as get_acceptance_tests. The 'authoritative fixed-scope' wording gives context but no exclusions or 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?

Annotations already mark the tool as read-only, idempotent, and open-world, so the core behavioral context is covered. The description adds useful specificity about what is not performed (create/fund/verify/start), but it does not add detail about response format, auth requirements, or offer selection. No contradiction with annotations.

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 the primary behavior front-loaded and the negative scope stated in a single clear sentence. Every word earns its place; there is no fluff or repetition of schema content.

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 simple two-parameter read-only tool with rich annotations, the description covers the core intent and explicitly rules out side effects. It is slightly incomplete in not pointing to how an offer is selected or that human authorization must be supplied, though the schema already documents the latter.

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 fully documents human_authorized_to_fund, and the description's 'selected offer' gives minimal but real meaning to offer_id. It does not explain the two cryptic offer_id enum values or connect them to a prior list/selection step, so the description only partially compensates for the schema's missing offer_id 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 clear verb ('Return') and resource ('machine-readable purchase-intent schema and API endpoint') for a selected offer. The explicit negative scope ('does not create, fund, verify, or start an order') clearly distinguishes it from action-oriented purchase tools and from the sibling 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?

The description implies it should be used when an offer is already selected and only the schema/endpoint is needed, and it warns against expecting side effects. However, it does not name alternatives or state when not to use it relative to siblings like qualify_task or list_offers.

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 readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds value by specifying exactly what is not performed (diagnosis, order creation) and what the routing outcome is, all consistent with the read-only annotation. No contradiction.

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 efficient sentences with zero waste. The routing action and three outcomes are front-loaded, with the safety negations placed immediately after. Every clause earns its place.

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 single-parameter tool with 100% schema coverage and strong annotations covering the safety profile, the description is nearly complete. Without an output schema, it usefully conveys the conceptual return (a routing decision among three defined options). It could name sibling tools but nothing essential for invoking 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% — the single 'summary' parameter is fully described in the schema with length constraints and content rules. The description's 'sanitized task summary' phrasing reinforces what the schema already states but doesn't add substantive new meaning, so the baseline of 3 is appropriate.

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 (route) with a clear resource (sanitized task summary) and enumerates the three concrete outcomes (fixed offer, broader Zinvyl service, scope reduction). This is specific enough to convey what the tool does, though it doesn't explicitly name siblings to differentiate itself.

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 exclusions 'performs no diagnosis and creates no order' provide clear when-not guidance that helps an agent rule out this tool for diagnostic or order-creating tasks. However, it doesn't name alternative tools or state positive conditions for choosing it over siblings like prepare_purchase_route.

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