Daski

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

Annotations only declare the safety profile (not read-only, destructive, non-idempotent, open-world); the description goes well beyond that by disclosing the two-phase x402 flow, exactly which fields must be repeated on retry, and the preferred vs expert payment channels (_meta["x402/payment"] vs paymentPayload). This is the kind of protocol-level behavior an agent cannot infer from structured fields.

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 dense sentences, front-loaded with the action and the retry mechanics, with no filler. The x402-specific terminology is compressed but every clause carries information the agent needs.

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 an output schema exists, return values need not be described, and the description covers the full mutation flow including the two-step retry contract and payment placement. The only residual gap is the unmentioned payerAddress, which is minor for a well-annotated, schema-backed tool.

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?

With 0% schema description coverage, the description must carry the burden, and it meaningfully explains providerAgentId, outcomeId, request (must be identical on retry), and both payment-carrying fields along with their preferred/expert ranking. It omits any explanation of payerAddress, leaving one of the five parameters undocumented.

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 specific verb and resource ("Buy one committed Daski outcome") and scopes it to a single outcome, which distinguishes it from list/read siblings like daski_list_outcomes and daski_get_outcome. It does not, however, explicitly name a sibling it must not be confused with, so it falls short of full sibling differentiation.

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 gives clear procedural context: the first call returns a payment requirement and a retry with identical identifiers plus signed payment completes the purchase, which tells the agent exactly when and how to invoke it. It stops short of naming alternatives or prerequisites (e.g., that requirements must be fetched first, or that input-bearing outcomes need the nonce recipe from another tool) as explicit routing instructions.

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 flag destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is partly covered. The description adds valuable non-structured behavior: the challenge/retry authorization handshake and that the challenge is short-lived, which is exactly the kind of 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?

Two tight sentences, front-loaded with the purpose before the procedural detail, with no filler 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?

An output schema exists, so return values need not be described, and the description adequately covers the multi-step auth flow for a destructive mutation. It falls short only in not explaining how the challenge obtained on the first call relates to the authorization object passed on the retry.

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% with three parameters including a nested authorization object, so the schema alone leaves fields undocumented. The description implies the role of `authorization` (payer's EIP-712 signature) and the first-call/second-call distinction, but says nothing about `orderHandle` or what `request` should contain.

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 ('Request cancellation of an order'), which cleanly distinguishes it from read-oriented siblings like daski_get_order_status and from daski_confirm_delivery. It is clear but does not explicitly name which sibling it replaces or complements.

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 concrete procedural guidance: call once without authorization to obtain a short-lived challenge, then retry with the payer's EIP-712 authorization. This is real when/how guidance for the two-phase flow, though it never addresses when to prefer this over alternatives such as contacting support.

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 destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that: the challenge/retry authorization handshake and the relay-vs-direct semantics of the EAS attestation. It stops short of saying which phase is destructive or that submit is irreversible, leaving some ambiguity.

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, front-loaded with the purpose, and every sentence carries content about modes or the auth flow. The middle sentence is dense and slightly hard to parse on first read, but there is 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?

An output schema exists so return values need not be described, and annotations carry the safety profile. Given a mutation tool with a nested auth object, the description covers the essential invocation flow and the prepare/submit/check distinction; only the authorization payload and the exact destructive consequence remain unaddressed.

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 0% and the `request` object is opaque (additionalProperties: {}), so the description's note that the request carries `phase` and `submission` adds genuine meaning the schema cannot. However, the entire nine-field `authorization` object and `orderHandle` are undocumented anywhere, so the description only partially compensates.

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?

Names a specific resource (payer-signed delivery confirmation) and enumerates the three modes it serves (prepare/submit/check), which is enough to distinguish it from siblings like daski_revoke_delivery_confirmation. It does not explicitly contrast itself with those siblings, so it stops 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?

Gives concrete operational routing — when to use sponsored vs direct submission based on wallet type — and states the non-obvious invocation flow: call once unauthorized to get an order-action challenge, then retry with a fresh payer authorization. No explicit 'do not use this when...' or sibling alternative is offered, so not a 5.

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=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds non-obvious behavioral context: the short-lived challenge flow and the payer EIP-712 authorization requirement, though it does not describe side effects or failure 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?

Two sentences, front-loaded with the action, then the critical auth sequence. Every sentence earns its place with 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?

The description covers the behavioral flow and complements the annotations, but the tool has nested objects and 0% schema description coverage, leaving key parameters unexplained. An output schema exists, so return values need not be described.

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 for parameter meaning. It only clarifies the role of authorization in the retry step and leaves orderHandle and the nested request/requestId/message fields undocumented.

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 specific verb and resource: sending a support request for an order. It is clear enough for an agent to understand the core action, but it does not distinguish this tool from any sibling by comparison or scope.

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 prescribes a two-step call sequence: first without authorization to receive a short-lived challenge, then retry with the payer's EIP-712 authorization. This is clear usage context, though it does not state when not to use the tool versus 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 declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The word 'private' hints at access scoping, but the description never discloses that an authorization/signature payload appears required, nor what 'aggregate participation' returns. Little behavioral context beyond the 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?

A single tight sentence with the scope modifier front-loaded and 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?

Output schema exists so return values need not be described, but for a tool requiring a complex signed authorization payload the description omits any mention of authentication or prerequisites, leaving a significant gap.

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% and the second parameter is a deeply nested authorization object with 17 required signing fields. The description only echoes 'payer wallet' and says nothing about authorization, signing, or the required 0x-address format, so it fails to compensate for the coverage gap.

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 (private aggregate Daski reputation participation) scoped to a payer wallet. Clear enough to distinguish from the order/outcome/provider siblings, though it doesn't name which sibling might be an alternative.

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?

No when-to-use, when-not-to-use, or alternative is mentioned. The description gives no context for selecting this tool over the other daski_get_* tools.

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/destructive/idempotent hints, but the description adds genuinely new behavioral detail: the capability is short-lived, and the call is a two-phase challenge-then-signature flow requiring a payer signature. The main missing piece is that the description's 'mint' framing sits in mild tension with readOnlyHint without explanation.

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, front-loaded with the purpose and then the two-step procedure. 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?

The output schema means return values need not be described, and the two-phase flow is stated. But for a tool whose entire complexity lives in the authorization payload, the description leaves the agent without the parameter-level detail needed to complete the second call correctly.

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% and the schema is a nested authorization object with nine required fields. The description only alludes to 'the payer signature' and never explains orderHandle or how the authorization fields (nonce, requestHash, validBefore, etc.) relate to the challenge returned by the first call.

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 gives a specific verb ('Mint') and resource ('short-lived capability for repeated status and artifact reads'), which clearly distinguishes it from the direct-read siblings daski_get_order_status and daski_get_order_artifact. It does not, however, explicitly name those siblings to steer selection.

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 gives clear procedural context: call once for a sign-ready grant-read challenge, then retry with the payer signature. That is real when-to-use guidance, though it stops short of stating when to prefer this over one-shot status/artifact reads.

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/idempotentHint/openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: the two-phase challenge-then-authorize handshake and the 'short-lived' nature of the challenge, which is not derivable from annotations or 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 tight sentences, zero filler, and the resource scope is front-loaded ahead of the invocation sequence. Every sentence 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?

An output schema exists, so return values need not be described. But with a nested 9-field authorization object, a large readCapability string, and 0% schema coverage, the description accounts for only part of the input surface and omits the nature of readCapability entirely.

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% across 4 parameters, so the description must carry the load. It adds meaning for one parameter by naming the EIP-712 payer authorization and the challenge flow that produces it, but leaves orderHandle, request, and especially readCapability (80–2048 chars) entirely unexplained.

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 (Retrieve) and a precise resource (the protected result artifact for a completed order). 'Protected result artifact' and the 'completed order' scope distinguish it from siblings like get_order_access, get_order_status, and get_outcome, though no sibling is named explicitly.

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 explicit procedural guidance for invocation: call once without authorization to obtain a short-lived challenge, then retry with the payer's EIP-712 authorization. It does not, however, state when to prefer this over sibling retrieval tools or prerequisites for order state.

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, openWorld, and non-destructive traits. The description adds an important behavioral detail beyond annotations: a two-step authorization challenge flow with a short-lived challenge, which is essential for correct invocation.

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, front-loaded with the purpose and then the critical auth flow. No wasted words; every sentence 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?

The description covers the complex authorization handshake, which is the hardest part. But with 0% schema description coverage, four parameters, and nested objects, it leaves required parameter orderHandle and optional readCapability unexplained. Output schema and annotations reduce the burden elsewhere.

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% and the description mentions only the authorization parameter, giving its EIP-712 nature. It does not explain the required orderHandle, the request object, or readCapability, leaving most parameter semantics undocumented.

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 clear verb+resource: get the current state of a purchased outcome. It aligns with the tool name daski_get_order_status but does not explicitly distinguish it from siblings like daski_get_outcome or daski_get_order_access.

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 a clear procedural context: call once without authorization to receive a short-lived challenge, then retry with the payer's EIP-712 authorization. It does not name alternative tools or state when not to use this one, but the when-to-use is strongly implied.

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, so the bar is lower, yet the description adds real value: output is 'capped for tool output' and presentation text is provider-authored and must be treated as untrusted data. That prompt-injection warning is behaviorally important and not derivable from structured fields.

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?

Dense but earns its length: the primary purpose is front-loaded, then the payload inventory, then the safety caveat. Two sentences with near-zero filler for a rich payload, though the middle clause runs long.

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 needn't be explained, and annotations cover the safety profile; the description even summarizes output contents. However, with 0% parameter description coverage and no sibling routing, it is incomplete for an agent that must decide between this and daski_get_outcome_requirements.

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 carries the full burden, but it only vaguely implies outcomeId via 'one admitted Daski outcome' and says nothing about providerAgentId, its numeric pattern, or that both are required. Two undocumented required parameters leave the agent guessing at their meaning.

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 ('one admitted Daski outcome') and enumerates the payload contents (schemas, provenance, policies, reputation). It implies singularity, distinguishing it from daski_list_outcomes, but never names a sibling to sharpen the boundary against daski_get_outcome_requirements.

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 phrase 'one admitted Daski outcome' weakly signals this is the single-outcome fetch after admission, but there is no explicit when-to-use, when-not, or routing to alternatives like daski_get_outcome_requirements. Usage is inferable but not stated.

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, idempotent, and non-destructive, so the safety bar is met structurally. The description adds real value beyond them by clarifying it reads catalog data with no order/price/payment side effects and by noting 'Provider descriptions remain data' – a prompt-injection safety cue. It does not cover output shape or any rate/limit 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?

Three sentences, front-loaded with the verb and outputs before the behavioral caveats. Every sentence carries information, with only mild redundancy in the list of negative actions.

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 required, and the description adequately frames what the tool reads and what it deliberately avoids. The remaining gap is parameter guidance, which is thin given the zero schema coverage and the nested request object.

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 carry the burden. It only hints that the agent should 'supply known details such as state and entity type,' which loosely maps to the free-form request object, but providerAgentId and outcomeId (both required) and the structured contents of request are never explained.

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 (outcome requirements) and enumerates the concrete outputs: published request schema, conditional intake requirements, normalized selectors, and missing fields. This is clearly distinct from the bare daski_get_outcome sibling, though it never names that sibling explicitly to draw the contrast.

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?

"Supply known details such as state and entity type" gives concrete usage context, and the description explicitly excludes what it is not (creating an order, requesting a binding price quote, submitting payment), which routes the agent away from daski_buy_outcome and order-mutating siblings. It stops short of naming which sibling to use when the agent actually wants to buy or price.

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=false, idempotentHint=true, destructiveHint=false, and openWorldHint=true; the description confirms this is a non-destructive draft creation that is safe to reuse, and adds concrete behavioral context beyond the annotations: no payment is submitted, the returned challenge is what the paid retry must bind to, and the preflight is non-blocking. It does not state auth/permission requirements or what happens to a previously bound challenge on retry.

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, front-loaded with the primary action and its key constraint (no payment submitted), followed by what is returned and the retry binding rule. No filler; each sentence carries an actionable fact.

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 not be spelled out, and the description still usefully characterizes the return (bound x402 challenge plus non-blocking payer balance/eligibility preflight). For a mutation tool with a nested request object, the main remaining gap is the undocumented payerAddress and the structure of `request`.

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 has to compensate. It explicitly names three of the four parameters (providerAgentId, outcomeId, request) and adds the important constraint that the paid retry must carry the identical values, which the schema cannot convey. However, it says nothing about the contents/shape of the nested `request` object or about payerAddress, leaving half the parameter surface unexplained.

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 compound action (obtain a binding quote; create or reuse a draft order) and explicitly scopes it as not submitting payment. It also names the sibling that performs the payment step (daski_buy_outcome), so the agent can separate the prepare tool from the buy tool 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?

The description makes the call sequence clear: this is the pre-payment step whose challenge feeds daski_buy_outcome, and the retry must reuse the same providerAgentId, outcomeId, and request. It stops short of stating explicit exclusions (e.g., when not to call it, or how it relates to daski_get_order_status / daski_cancel_order for an existing draft).

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, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered. The description adds only that the read is a composite of identity, catalog services, and reputation, and says nothing about not-found behavior, data freshness, or cost — an incremental but small contribution over the 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?

A single declarative sentence that front-loads the verb and enumerates the returned facets without filler. Nothing could be trimmed without losing 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?

An output schema exists, so return shape need not be described, and annotations carry the safety profile. What is missing is how to obtain a valid agentId and what happens when the provider is unknown — relevant for a read-by-id tool in a marketplace with many sibling lookup tools.

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% and the single parameter is a constrained numeric string (pattern ^(0|[1-9]\d{0,77})$), yet the description never explains what an agentId is or where to obtain one. The description provides zero compensation for the coverage gap; only the self-descriptive name carries any meaning.

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 specific verb (Read) and resource (a provider's canonical identity, catalog services, and reputation), which is far more than a restatement of the name. It implicitly separates itself from daski_list_providers (plural, listing) and daski_get_my_reputation (self vs provider), but never names those siblings explicitly.

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?

There is no statement of when to use this tool versus daski_list_providers, daski_resolve_agent, or daski_get_service, and no preconditions (e.g., needing a known agentId). Usage can only be inferred from the tool name, which is the definition of no guidance.

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, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is fully covered by structured data. The description's only added behavioral signal is 'on-chain', which hints that the read hits a blockchain source, but it says nothing about latency, availability, or what happens when the record does not 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?

A single front-loaded sentence with no filler and no redundancy. It is efficient, though the brevity borders on under-specification rather than deliberate concision.

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 annotations cover the safety profile, which lowers the burden considerably. Still, for a tool whose only input is an opaque on-chain identifier, the description omits both the meaning of serviceId and any usage context, leaving meaningful gaps.

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% for the single required serviceId parameter, and the description does not compensate by explaining what the identifier refers to, where it comes from, or how to obtain it. Only the schema's regex pattern hints at the 32-byte hex format, so the agent gets the shape but not the semantics.

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') and a specific resource ('on-chain Daski service-catalog record'), which is enough to distinguish it from action siblings like daski_buy_outcome or daski_confirm_delivery. It does not, however, contrast itself with the other read siblings (daski_get_provider, daski_get_outcome), so differentiation relies on the resource noun alone.

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?

There is no statement of when to use this tool versus alternatives such as daski_get_provider or daski_list_providers, and no prerequisites or context cues. The agent must infer usage purely from the name and the record type.

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 burden is light. The description adds real context beyond them: the return is the canonical text verbatim (not a summary) and carries a sha256 for integrity verification.

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 verbatim/checksum guarantee and the topic list come first, and the routing advice follows. 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?

An output schema exists, so return-value details need not be spelled out. For a single optional-enum, read-only retrieval tool, the description covers purpose, alternative routing, and output guarantees with nothing material 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 single `topic` parameter has 0% schema description coverage, but its enum values are self-explanatory and the description maps them to prose (setup, buying, orders, wallets) and clarifies that 'recipe' means the nonce recipe. That added gloss compensates for the missing 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?

States a specific verb (return) and resource (canonical Daski guide) and enumerates the five topics the guide covers. 'Verbatim with its sha256' further pins down the exact output form, so the agent can distinguish it from any summarization 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?

Explicitly says 'Prefer this over fetching the guide's URL through a tool that summarizes pages,' naming the alternative class and the reason (verbatim vs summarized). No specific sibling tool is named, so it stops just 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.

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds only the ownership/wallet scoping statement and says nothing about pagination behavior, that an authorization signature may be required, or anything about how the 'connected payer wallet' is established.

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 with no wasted words. It is efficient, though arguably too terse for the underlying parameter complexity.

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 not be explained, but for a tool with 5 parameters (including a signed authorization blob) and 0% schema description coverage, the description omits pagination, credential, and filtering context an agent would need to call it correctly.

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% across 5 parameters, including a nested authorization object with a full signed message. The description never mentions payer, limit, cursor, providerAgentId, or authorization, and gives no hint about pagination or auth requirements, so it does not compensate for the coverage gap.

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 ('List provider-owned assets') and adds a meaningful scope qualifier ('controlled by the connected payer wallet'), which separates it from write-side siblings like daski_use_asset. It does not explicitly name an alternative tool, so it doesn't reach 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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The agent must infer from the name alone that this is the read-only enumeration counterpart to daski_use_asset.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one piece of real context: results are 'private' and limited to the connected payer wallet's own history. However, it says nothing about the authorization object requirement (a signed message), pagination behavior, or rate/visibility limits, which matters given the tool accepts a complex signed authorization parameter.

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 with no filler, so it is efficient and well-structured. It is arguably too terse for a tool with a signed-authorization parameter, but that under-specification is captured under contextual completeness rather than penalized here.

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?

The tool has 5 parameters, a nested authorization object, and a 0%-described schema, so the description carries a heavy disclosure burden. It offers only one sentence with no explanation of the auth flow, cursor-based pagination, or parameter meanings. An output schema exists, so return values needn't be explained, but the invocation prerequisites are severely under-documented.

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% across 5 parameters, including a large nested authorization object, so the schema provides no semantic help. The description only weakly implies the meaning of payer ('connected payer wallet') and says nothing about limit, cursor, authorization, or paymentIdentifier. It does not compensate for the coverage gap.

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 gives a specific verb (List) and resource (the payer wallet's Daski order history), which is far clearer than a tautology. It scopes the operation to the 'connected payer wallet', but it doesn't name or contrast itself with the many sibling list/get tools (e.g. daski_get_order_status, daski_list_assets), so an agent must infer the distinction. Clear purpose, lacking sibling differentiation.

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?

There is no explicit when-to-use or when-not-to-use guidance, no mention of prerequisites, and no named alternative tool. The phrase 'connected payer wallet's private' weakly implies this only returns the caller's own orders, but no condition selects it over siblings like daski_get_order_status. Essentially no usage guidance.

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 the read-only/idempotent/non-destructive profile, but the description adds real behavioral detail beyond them: filters AND together, substring-no-stemming token matching, the zero-hit `searchHint` behavior with live catalog vocabulary, compact-row returns, and an explicit prompt-injection warning that provider-authored names/descriptions/tags are untrusted data. That is well beyond what the annotations disclose.

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 dense paragraph that front-loads what the tool searches and then moves to filter semantics; almost every clause carries operational information. It is on the long side for a list tool, but there is no filler 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?

An output schema exists, so return values need not be spelled out, and the description still adds the useful note about compact rows and the zero-hit searchHint. The main gap is the four parameters with no explanation in either the schema or the description, which leaves parts of the invocation contract underspecified.

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 carry the burden and it does so for only four of eight parameters: text matching semantics and the controlled-id expectations for categoryFamily, serviceType, and jurisdiction (ISO 3166-1/3166-2/'global', with the note that country and subdivision filters match each other's listings). limit, pricingMode, persistentAsset, and providerAgentId are never mentioned, so half the surface remains undocumented.

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 with scope: 'Search the currently admitted, purchasable Daski outcomes.' It explicitly distinguishes itself from the sibling that returns detail ('Full detail ... via daski_get_outcome'), so an agent can separate the search tool from the fetch tool 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?

Gives explicit when-to-use guidance for the text filter ('use product words (llc, domain, mailbox), not sentences'), names the controlled-vocabulary parameters and their expected id formats, and routes to daski_get_outcome when full detail is needed. The alternative and the condition that selects it are both stated.

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, idempotentHint, openWorldHint and destructiveHint=false, so safety semantics are covered structurally. The description adds only the domain framing ('on-chain marketplace catalog'), which mildly reinforces the open-world nature but discloses nothing about pagination behavior or result volume.

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 efficient sentence with the resource and scope front-loaded and no filler. It is well-sized, though its brevity contributes to the missing usage and parameter guidance.

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 not be described, and annotations carry the safety profile. However, with two undocumented pagination parameters and no usage guidance or sibling routing, the definition is only minimally complete for an agent to call it correctly.

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?

Both parameters (limit, offset) have 0% schema description coverage and are also unmentioned in the description, so an agent gets no textual explanation of pagination, defaults, or the 1-100 / 0-1000000 bounds. The description does not compensate for the coverage gap.

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 gives a specific verb+resource ('List providers') scoped to the 'Daski on-chain marketplace catalog', which is unambiguous and distinguishable from the singular daski_get_provider. It does not explicitly distinguish itself from other list-style siblings (daski_list_assets, daski_list_outcomes), so it stops 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?

There is no when-to-use guidance, no mention of pagination flow, and no pointer to sibling tools such as daski_get_provider for single-record lookups. The agent must infer applicability purely from the name and one-line description.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds one useful behavioral fact — the index is 'verified', implying unverified wallets may not resolve — but says nothing about auth needs, not-found behavior, or latency.

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 with the action first and the qualifier ('verified... index') second. No filler, no redundant restatement of the name.

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 not be explained, and annotations cover the safety profile. However, for an open-world read that could fail on an unindexed wallet, the description omits error/not-found semantics and any access requirements — a modest but real gap.

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% and the sole parameter carries only a regex pattern, so the description must compensate for the missing prose. It mentions 'wallet' but adds no format, source, or constraint detail (e.g., that it is a 0x-prefixed 40-hex address); the pattern alone is doing the work.

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 (resolve) and resource (a wallet) plus the target of the lookup (Daski's verified wallet-to-ERC-8004 agent index). No sibling tool performs wallet-to-agent resolution, so it is implicitly distinct, though the description never explicitly contrasts itself with the provider/order-focused 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?

No when-to-use guidance, no preconditions (e.g., whether the wallet must already be indexed), and no mention of what to do when resolution fails. The name and one-line purpose imply the scenario, but nothing is stated that helps an agent choose or sequence this call.

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 destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-derivable behavior: the two-step challenge/retry authorization handshake and the difference between relayed EAS attestation and a wallet-issued validated call. It does not restate the destructive or non-idempotent nature, which would have been useful for a withdrawal operation.

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, front-loaded with the operation and then the request-shape detail, with no filler. The parenthetical enumerations are dense but each clause carries information. Slightly heavy nesting inside the second sentence keeps it from a 5.

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 not be explained, and the description covers the multi-phase flow and the auth handshake adequately for a complex, nested-parameter tool. It omits any mention of irreversibility or repeated-call behavior, which matters for a destructive, non-idempotent operation with a 0%-documented schema.

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% and one parameter (request) is an opaque free-form object, so the description must carry the load. It partially does: it explains that 'request' carries phase (prepare/submit/check) and submission (sponsored/direct), which the schema cannot convey. However, orderHandle and the nine-field authorization object receive no explanation, so the coverage gap is only partly closed.

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 specific resource (the payer's current delivery confirmation) and three concrete operations (prepare/submit/check withdrawal), so the agent knows exactly what the tool manipulates. It does not explicitly differentiate itself from the adjacent sibling daski_confirm_delivery, which is the most likely confusion point, so it falls 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 gives concrete when-to-use guidance: which phase value maps to which intent, and when to choose 'sponsored' vs 'direct' submission. It also states the auth flow explicitly ('call once without authorization for an order-action challenge, then retry with a fresh payer authorization'). It never says when NOT to use this tool or which sibling handles the non-withdrawal path.

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 a non-read-only, non-idempotent, open-world write, and the description adds the key behavioral trait those annotations miss: a two-phase challenge/response flow requiring the payer's EIP-712 authorization. It notes the challenge is short-lived, which is meaningful context. It could say more about what happens on a second submission, but this is a solid addition beyond the structured fields.

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, purpose front-loaded, with the flow described second. No filler. It is appropriately sized and would only improve by adding a clause on parameters or prerequisites.

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 and annotations exist, so return values and safety profile need not be restated. The core purpose and the auth flow are conveyed, but for a tool with a nested authorization object and zero schema descriptions, the definition leaves notable gaps about the request payload and orderHandle semantics.

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% across three parameters (request, orderHandle, authorization), a nested object among them, so the description must carry the burden. It only gestures at 'authorization' (EIP-712) and never explains 'request' or 'orderHandle' or how the challenge maps to the authorization fields. Marginal compensation for a significant gap.

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 ('Submit') and resource ('requested customer input for an order'), clearly naming what is being sent and to what. It does not explicitly contrast itself with siblings like daski_get_order_status or daski_buy_outcome, but the resource is distinctive enough that an agent can place it.

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 concrete call-sequence guidance: call once bare to obtain a short-lived challenge, then retry with authorization. That is useful invocation guidance, but it says nothing about when to use this tool versus alternatives or what prerequisites (e.g., an existing order) are required.

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 destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds that the action must be "admitted" and that the asset is payer-controlled, which hints at an authorization gate, but it says nothing about the required signed authorization payload or side effects, so the added value is modest.

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 with no filler, which is efficient. Brevity comes at the cost of completeness here, but the sentence itself is well-formed and wastes nothing.

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 destructive, non-idempotent tool with nested signed authorization, 0% schema coverage, and five required parameters, this one-liner is materially under-specified. The output schema exists so return values need not be described, but the mechanism and preconditions for a valid call 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 description coverage is 0% across 6 parameters, including a deeply nested signed-authorization object, so the description carries full burden. It only obliquely references the payer wallet and the asset; actionId, providerAgentId, input, and the entire authorization message are left completely unexplained.

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 verb/resource pair ("run ... action against an asset") gives a rough sense of a state-changing operation on an asset, which distinguishes it from read-oriented siblings like daski_list_assets. However, the core term "admitted provider action" is undefined jargon, so an agent cannot tell what the tool actually does at the domain level without external knowledge.

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?

There is no guidance on when to use this tool versus siblings such as daski_list_assets, daski_buy_outcome, or daski_submit_order_input, and no mention of prerequisites (e.g. needing an admission or authorization first). The agent must infer applicability entirely.

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