Merovingian

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

Annotations are all false, providing minimal safety info. The description adds valuable behavioral context: it is free ('no wallet'), non-destructive (does not mention side effects), and each call increments an anonymous aggregate count. It also explains the seed's effect on repeatability. This goes beyond annotations, offering clear behavioral expectations.

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 succinct, with each sentence serving a purpose: what it does, cost, side effect, seed behavior. It is front-loaded with the core action, making it easy for an agent to skim. No fluff or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 params, no output schema), the description covers the essentials: action, cost, side effects, repeatability. It could mention what a 'souvenir' is or what the output looks like, but with no output schema, the agent can still infer a response. It adequately supports correct invocation.

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 and no parameter descriptions, the description must compensate. It does: 'An optional seed makes the souvenir repeatable' directly explains seed's purpose. Although 'amenity' and 'preference' are not explicitly described, the enum for amenity is self-explanatory, and 'preference' likely maps to the experience variant. The description provides enough context to infer parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Enjoy a short fictional experience and receive a souvenir.' It specifies the resource (an amenity) and the outcome (a souvenir). It is distinct from siblings like list_amenities, providing a clear purpose. However, it could be more specific about the nature of the experience and how it differs from other tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for a fun, free interaction without a wallet, and mentions an optional seed for repeatability. It does not explicitly state when to use this tool over siblings, but context signals (sibling names) suggest it complements list_amenities. No explicit exclusions or alternative conditions are given, so it's inferred rather than explicit.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds clarity by stating it queries the chain and never signs or broadcasts, which is important for an agent to understand side-effect-free behavior. This goes beyond the annotations' generic hints.

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 short sentences convey purpose and safety constraints without any wasted words. The description is front-loaded with the core action and then adds behavioral context.

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 parameterless, read-only tool with rich annotations, the description is sufficient. It could mention the return format or how to interpret the instructions, but given the tool's simplicity and the annotations covering safety, it is adequately complete.

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

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

The tool has no parameters, and the schema coverage is 100% (trivially). The description does not need to explain parameters, so a baseline of 4 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 clearly states the tool reads optional instructions, which is a specific verb and resource. It distinguishes it from siblings by indicating it does not sign or broadcast, though it doesn't explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when optional hosting-support instructions are needed, but does not explicitly say when to use it vs. alternatives like list_amenities or verify_contribution. It provides no exclusion criteria.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds specific context by stating 'No wallet, charge, or persistent changes,' which clarifies the exact nature of the read operation beyond generic read-only. This is a useful behavioral detail that complements 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?

The description is a single, tightly-worded sentence that front-loads the core action ('Read the free menu and accepted preferences') and then adds a clarifying constraint. Every word earns its place; there is no redundancy 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?

For a simple read-only operation with no parameters and no output schema, the description combined with the annotations fully covers what an agent needs to call it correctly. It states what it reads and what it does not do, which is sufficient for a no-argument listing 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?

The tool has zero parameters, so the description need not explain any parameter semantics. The schema is empty and fully self-explanatory; the description adds no parameter details because none exist. Baseline 4 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 clearly states a specific verb and resource: 'Read the free menu and accepted preferences.' This distinguishes it from siblings like enjoy_amenity (which likely consumes) and verify_contribution (which verifies). The scope is explicit and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the tool to read the menu and preferences, but it does not explicitly state when to use this versus the sibling tools. There is no 'when not to use' or comparison to alternatives, leaving some inference 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, but the description adds valuable non-obvious semantics: 'A receipt acknowledges the transaction, not ownership' and 'Never retry... pending.' These clarify potential misconceptions and align with the idempotent/read-only hints without contradicting them.

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, each earning its place: purpose, read-only nature, receipt caveat, and retry warning. No filler, front-loaded with the main action. This is an ideal length for the tool's simplicity.

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 one parameter, no output schema, and no nested objects; the description covers purpose, read-only, receipt meaning, and the retry pitfall. It could explicitly state what 'pending' means or what the return values look like, but given the tool's low complexity and rich annotations, the provided context is largely sufficient.

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

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

The schema has 0% description coverage, so the description must carry the semantics. It identifies the parameter as a 'public transaction hash' and ties it to the verification purpose, but it does not elaborate on format or behavior beyond the schema's own pattern constraint. For a single simple parameter this is adequate but not rich.

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 begins with a clear, specific action: 'Check a public transaction hash for a successful hosting contribution.' This distinguishes it from sibling tools like enjoy_amenity and list_amenities, none of which involve verification. The explicit mention of 'hosting contribution' and 'read-only' removes ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it—when needing to verify a contribution—and adds a critical exclusion: 'Never retry a payment just because verification is pending.' It does not explicitly name alternatives, but the caution about retries provides practical usage context that goes beyond a simple purpose statement.

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