Decision Intelligence

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

There are no annotations, so the description carries full responsibility for behavioral disclosure. It reveals the cost ($0.08/call) but does not mention whether the tool mutates state, what 'unsent action findings' means, or any side effects. The schema later notes the Actor never fetches source URLs, but that is not in the description, leaving a significant transparency gap.

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 sentence followed by a pricing note, with zero filler. It front-loads the main action and includes only the essential cost detail. Every word earns its place, making it an exemplary model of conciseness.

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?

Despite the tool's complexity (13 parameters, nested options, no output schema), the description offers only a one-line purpose and price. It fails to describe the return format, the concept of 'unsent action', or any operational constraints. This leaves the agent without sufficient context to fully understand the tool's behavior.

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 input schema has 100% description coverage for all parameters, so the schema already documents every field meaningfully. The tool description adds no parameter-level detail beyond what the schema provides, relying fully on the schema—this matches the baseline expectation for high schema coverage.

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 action—'Compare supplied app reviews around a release'—and defines the output as 'regression and unsent action findings.' This is a distinctive capability not shared by the sibling tools (competitor-ad-change-brief, pricing_info, us-map-retail-evidence), so it stands out immediately.

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

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

The description provides clear context by specifying the domain (app reviews around a release) and the purpose (regression analysis). It doesn't explicitly discuss when-not-to-use or alternatives, but since none of the sibling tools overlap, that exclusion is not necessary. The guidance is implied 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It does disclose that the operation is deterministic and that it returns 'unsent actions' (implying no external sends), and it transparently states the pricing model ($0.10/call). However, it omits details about whether the operation is strictly read-only, authentication requirements, or any side effects beyond returning data, leaving significant behavioral uncertainty.

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 extremely concise: one summary sentence plus a pricing note. It front-loads the core purpose immediately and contains zero redundant or filler content. Every word earns its place.

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

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

The tool has a highly complex input schema (nested objects, conditional allOf/oneOf constraints, 11 parameters) and no output schema. The description only names three high-level outputs (changes, baseline state, unsent actions) without explaining their structure or semantic meaning. It also does not clarify the two mutually exclusive input modes (rows vs datasetId) or the purpose of the required provenance fields, making it insufficient for an agent to invoke correctly without significant schema parsing.

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 description covers 0% of the 11 parameters, and the schema itself lacks descriptive text for properties. The only hint is 'supplied ad evidence,' which vaguely maps to the rows or datasetId parameters, but critical required fields like coverage, sourceContract, requestId, and watchId are not explained. The description fails to compensate for the low schema coverage, leaving an agent without semantic guidance for constructing valid input.

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 function: 'Compare supplied ad evidence and return deterministic changes, baseline state, and unsent actions.' It uses a specific verb ('compare'), identifies the resource ('ad evidence'), and lists the specific outputs, making its purpose unambiguous and distinct from the unrelated sibling tools.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It merely states the action without contextual cues such as 'use this when...' or mentioning any sibling tool. The usage context is only implied by the generic 'supplied ad evidence' phrase.

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 states 'Free' and 'list,' implying a read-only, no-cost operation. However, it doesn't disclose potential side effects, data freshness, or pagination, leaving some behavioral 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?

The description is two short sentences, front-loaded with 'Free' and the core action. Every word contributes, earning a perfect score.

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 zero parameters and no output schema, the description conveys the return fields (price, payTo, network) and the calling context. It could mention the format of the list, but it's adequate for a simple 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 baseline is 4. The description adds no parameter details since none exist, but schema coverage is effectively 100% (empty 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 clearly states the tool lists every paid tool in the 'decision-intelligence' bundle with its price, payTo address, and network. The verb 'list' plus a specific resource distinguishes it from sibling tools, which appear unrelated to pricing.

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 says 'Call this first if you don't have a wallet ready yet,' giving a clear contextual trigger. It doesn't name alternatives, but no pricing siblings exist, so the guidance is sufficient.

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 of behavioral disclosure. It mentions that input is 'supplied' and that MAP, availability, baseline, and review findings are produced, but it does not disclose side effects, permissions, idempotency, error behavior, or return format. The pricing note is not behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that states the core action and outputs, followed by a concise cost note. There is no filler or redundancy; every element 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 tool has a complex schema with 9 parameters, nested objects, no output schema, and no annotations. A one-sentence description cannot adequately cover the rows-versus-datasetId choice, watchUniverse format, option semantics, or processing expectations, so the description is insufficient for reliable 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?

Schema description coverage is only 11%, and the description does not name or explain any parameters. The term 'supplied' weakly hints at rows or dataset input, but the description does not compensate for the lack of parameter documentation in the schema, especially given the complex nested structures.

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 uses a specific verb ('Process') and resource ('supplied US retail evidence') and states the outcome categories (MAP, availability, baseline, and review findings), clearly conveying the tool's function. It does not explicitly contrast with sibling tools, but the domain is distinct enough to avoid major confusion.

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 guidance on when to use this tool versus alternatives, no exclusions, and no reference to sibling tools. The phrase 'supplied US retail evidence' implies the input should be retailer-observed data, but this is not enough to guide an agent in choosing this over other tools.

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