kevaremesh

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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds meaningful context: no wallet, provider execution, payment or signup is required, and it describes what is returned (input-contract links, free preview links, current merchant-authorized payment eligibility). This goes beyond the safety profile annotations. The one gap is that return format details are still somewhat abstract without an 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?

The description is front-loaded with the core purpose and then adds returns and the sibling alternative, with no obvious filler. A few clauses (e.g., 'current merchant-authorized payment eligibility') are dense but still earn their place by preventing misuse.

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 discovery tool with rich annotations but no output schema, the description covers what it returns, what it excludes, and the alternative route. The only missing piece is clarity on the limit parameter's effect, which is minor given the tool's low complexity.

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 only 50%: the query parameter has a useful description in the schema, but the limit parameter has bounds and a default with no description anywhere. The tool description adds no parameter-level meaning or guidance (e.g., how to phrase a query, what limit controls), so it fails to compensate for the undocumented limit.

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 (find/discover) and resource (KEVAREMESH's first-party API tools) with clear scope (free, read-only, deterministic tasks). It explicitly distinguishes itself from the sibling by naming kevaremesh_use for paid external APIs, so an agent can select it 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 says when to use this tool (structured data, JSON, CSV, Base64, URLs, timestamps, encoding) and when to use the alternative (paid external web/search/finance APIs via kevaremesh_use). It also warns against inferring paid availability from an indicative price, leaving no routing ambiguity.

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 description adds substantial context beyond the annotations: the lookup is free, it never charges or creates another payment, and it returns the existing receipt ID only when one is present. One tension remains: it calls the operation "read-only" while the annotations declare readOnlyHint=false, so an agent cannot tell whether the lookup itself writes a receipt record; this is a minor inconsistency rather than a substantive misdirection, because destructiveHint=false and idempotentHint=true agree with the description that the operation is safe.

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 precondition first, the parameter rule second, and the behavioral guarantees last. Nothing is wasted; the capitalized ONLY/EXACT/NEVER is emphatic but each word carries a distinct constraint.

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 no output schema, the description covers the happy path and the no-charge guarantee well. It is silent on what happens when no receipt exists, specifically whether the response is indistinguishable from a miss; for a privacy-preserving ledger lookup, that gap matters.

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%, so the schema itself already supplies the baseline documentation of the single parameter. The description still adds real value by saying the digest must be computed locally from the EXACT original Payment-Signature value and never the raw signature; this is operational guidance the schema does not 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?

The description names a specific verb and resource (recover an already-reserved owned-API receipt) and frames the exact situation it serves: the buyer paid and lost the HTTP response. It does not, however, say how it differs from the confusingly similar sibling kevaremesh_recover_owned_result, which an agent could easily confuse this with.

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?

"Use ONLY if the buyer already submitted a signed x402 payment but lost the HTTP receipt response" is a strong, explicit precondition that scopes usage, and the warning to send the hash rather than the raw signature is a useful guardrail. It stops short of a score of 5 because it does not name an alternative such as recover_owned_result or find_owned_api, so the agent must infer which tool to use when the receipt response was not lost.

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?

Adds substantial context beyond the annotations: the result cache is only 24 hours (a real time limit that changes call strategy), reconciliation performs no signing/charging, and receipt/transaction details must be kept private. This is consistent with idempotentHint=true and destructiveHint=false; readOnlyHint=false is coherent because reconcile touches on-chain state, and the description explicitly bounds that side effect.

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 dense sentences with no filler, and the hardest constraint (no new payment) lands early. The leading fragment 'For a buyer-held PRIVATE receipt ID...' reads slightly awkwardly as an opening and the cache TTL could be tighter, but nothing is wasted.

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 three params, no output schema, and low schema coverage, the description carries the burden well: it explains all three modes, the 24-hour result window, the no-charge guarantee, and the privacy requirement. The remaining gap is failure behavior — what status/result returns when the cache has expired or the receipt is unknown — which an agent would want before relying on the 24-hour boundary.

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 only 33% and the 'mode' enum has no per-value documentation, but the description compensates by mapping the three operations onto status/result/reconcile ('Check payment and delivery', 'reconcile... on-chain', 'retrieve the original result'). receipt_id and transaction_hash formats are already handled by schema patterns and the transaction_hash description; only the default and per-mode requirements are left implicit.

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 (recover) plus resource (already purchased API output) and enumerates the three concrete operations: status/delivery check, on-chain reconciliation, and cached result retrieval. The opening phrase 'For a buyer-held PRIVATE receipt ID' implicitly separates it from locate_owned_receipt/find_owned_api (you already have the receipt), but no sibling is named, so differentiation is inferred rather than stated.

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 a clear precondition ('buyer-held PRIVATE receipt ID from a previous purchase') and a hard exclusion ('reconciliation can confirm EXISTING settlement only'), which tells the agent this is never a substitute for a purchase flow. However it never names kevaremesh_locate_owned_receipt or kevaremesh_find_owned_api as the path when no receipt_id exists, leaving that 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?

With annotations already declaring openWorld=true, destructive=true, readOnly=false, and idempotent=false, the description adds substantial behavioral context: free discovery/quotes, a $0.001 route fee for executable external routes, buyer-direct upstream payments, and the PaymentRequired retry flow. It does not explicitly elaborate on destructiveness or non-idempotency, but the annotations already carry those safety signals.

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 front-loaded with the use case and follows with routing, pricing, and retry behavior. It is dense and jargon-heavy, especially around x402 and merchant release proof, but the length is largely justified by the broad meta-tool scope.

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 an 8-parameter, open-world, potentially destructive routing/purchase tool with no output schema, the description covers the execution and payment flow well but does not explain what successful responses look like. It also lacks explicit sibling-tool differentiation, leaving some operational context incomplete.

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 every parameter is already documented. The description reinforces that goal should contain only the desired result and that input is for owned API purchases, but it largely repeats schema-level guidance rather than adding new parameter 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?

The description states a clear capability-routing purpose: it resolves the requested external API capability, compares live x402 supply, selects a provider, and routes execution. It is much more specific than the name alone and lists concrete domains like Base64, web search, finance, and geocoding, though it does not explicitly distinguish itself from the sibling find/receipt/recover 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?

It gives clear usage context: use it when a task needs an external API capability, put only the desired result in goal, and retry the same tool after each x402 PaymentRequired step. It also states the merchant-release-proof condition and that discovery/quotes are free, but it does not explicitly compare when to choose the sibling tools instead.

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