Routavo

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

With no annotations, the description carries the full burden of disclosure, and it does address the key behavioral trait: calls are metered, and 'failed calls are recorded but cost nothing.' It doesn't explicitly state that successful calls incur charges or require a wallet, but 'meter it' plus the failure-cost note makes the paid nature clear. This is much more transparent than a bare 'call an API' description.

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 short sentences front-load the core action, routing modes, constraints, and failure-cost behavior, with no filler. Every sentence earns its place, and the most important information appears first.

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 18-parameter tool with plans, batches, budgets, quorum, payment, failover, and idempotency, the description only orients the agent to the single-call mode and two routing parameters. The schema is rich and 100% covered, so nothing is hidden, but the description fails to signal the tool's advanced capabilities and never mentions output structure. A more complete overview would at least hint at the plan/batch/budget/payment modes.

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 baseline is 3, but the description adds meaning beyond the schema by linking provider ids to discover() and explaining capability routing via 'published routing rule.' It also identifies max_price and max_latency_ms as the choice-constraining parameters, which helps the agent understand how the parameters work together. This goes slightly beyond simply repeating the schema's per-parameter 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 opens with a specific verb-resource pair: 'Route a call to the Routavo network, meter it, and return the result.' It then explains the two invocation modes (provider id vs. capability), which clearly distinguishes it from siblings like discover, dispute, and verify. It is not a tautology and tells the agent exactly what the tool does.

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 explicitly directs agents to 'give either a provider id from discover(), or a capability and let Routavo pick using its published routing rule,' which is clear when-to-use guidance for the two main invocation styles. It also names max_price and max_latency_ms as constraints, helping the agent choose parameters. It doesn't explicitly contrast with dispute or verify, but those are not natural alternatives to calling an API.

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

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

With no annotations, the description carries the full behavioral burden and succeeds: it discloses the returned fields (price, latency, terms, argument schema, selection rule), the ranked matching behavior, and the intended invocation context. There is no ambiguity about side effects or read-only status because the description frames it as a discovery/query 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 with no filler: the first states the action and output, the second lists the return payload, and the third gives the usage trigger. The most important guidance is front-loaded and 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?

For a two-optional-parameter discovery tool with a complete input schema and an output schema, the description covers invocation timing, output content, and the distinction from call(). Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema already provides rich descriptions for both query and capability. The tool description adds the conceptual context 'discovery before call' but does not add meaning to the parameters beyond what the schema already states, so baseline 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 ('find') and resource ('APIs on the Routavo network that can perform a capability'), and clearly distinguishes itself from call() by explaining it discovers providers before a provider id is known. It also enumerates exactly what is returned, so an agent can tell what the tool is for.

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 explicitly says 'Call this before call() when you do not already know a provider id,' which gives both a positive trigger and a clear contrast with the sibling call tool. This is exactly the kind of when-to-use guidance an agent needs.

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

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

With no annotations, the description carries the full burden and discloses real side effects: the dispute is placed in the provider's queue, is visible to Routavo, and is limited to one per receipt. It stops short of stating reversibility or auth requirements, but the important write-side behavior is clear.

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?

Five short sentences, each carrying distinct value: action, inputs, preconditions, destination/side effect, and unique constraint. 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?

For a two-parameter action with no output schema, the description covers what, when, preconditions, and consequences. It does not specify the return shape or error behavior, but those are not needed to invoke the tool 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 coverage is 100%, but the description adds beyond the schema by noting the reason should be short and that the receipt must verify and have charged something. It also connects the receipt parameter to the call() result implicitly through the mention of a metered 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 opens with a specific verb-resource pair ('Flag a metered call') and names the exact domain (disputing a charge). This clearly distinguishes it from sibling tools like call, discover, and verify by indicating this is the review/flagging action, not a creation or verification action.

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 preconditions: the receipt must verify and must have charged something, and one dispute is allowed per receipt. It does not explicitly name sibling alternatives or say when not to use them, but the conditions clearly gate when the tool applies.

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

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

With no annotations, the description carries the full burden. It does disclose key behavioral traits: signature confirmation, the specific fields verified, accessibility to anyone holding the receipt, and a privacy guarantee ('reveals nothing else'). However, it does not describe what happens on invalid signature (error vs. false return) or the return shape, which is a notable gap for an agent.

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?

Four short sentences, all informative. The main verb and object are front-loaded, and the privacy guarantee is a compact final sentence. No redundant phrases or 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 purpose, parameter source, and privacy, but does not specify the return value or behavior on invalid signatures. Since there is no output schema, the description should be more explicit about what the agent receives after verification, especially in failure cases.

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 baseline is 3. The description adds value beyond the schema by listing the receipt fields that are verified (provider, price, fee, hashes), which clues the agent into the expected structure and semantics of the receipt object.

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 ('Check/Confirms'), a specific resource ('a receipt returned by call()'), and enumerates exactly what is confirmed (provider, price, fee, and hashes). This clearly differentiates it from siblings like call, discover, and dispute, which all have distinct purposes.

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 context: use this when you hold a receipt returned by call() and need to confirm its authenticity. It does not explicitly name alternatives or describe when not to use it, so it falls short of a 5, but the purpose is specific enough that an agent would not confuse it with siblings.

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