AEO Audit

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

Annotations already declare readOnlyHint and openWorldHint, so the description adds value by specifying that it checks how a domain appears across AI answer engines and returns specific metrics. No contradictory or missing behavioral traits.

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 three concise sentences, each adding value: the main action, what is checked, and what is returned. No unnecessary words, and the structure is front-loaded.

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 there is no output schema, the description adequately covers return values (citation rate, grade, etc.) and the scope of the audit. However, it does not explain the grading scale or what 'full' entails, leaving minor 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 coverage is 100%, so parameters are well-documented in the schema. The description adds minimal new insight, only implicitly referencing competitors through 'competitor comparison' in the output.

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 it runs a full AEO audit for a domain, listing specific outputs like citation rate, grade, competitor comparison, and per-query results. This distinguishes it from siblings like quick_check (likely lighter) and audit_domain_premium (premium version).

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 explains what the tool does but does not provide explicit guidance on when to use it versus siblings like audit_domain_premium or quick_check. The usage context is implied but not stated, leaving the agent to infer.

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 provide readOnlyHint and openWorldHint. The description adds significant behavioral context: pricing model (subscription or per-call) and the detailed output structure (recommendations, implementation guide, competitive analysis, score improvement). This goes beyond annotations to help the agent understand the tool's cost and output richness. However, it doesn't mention rate limits or authentication beyond the payment link.

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 concise with a clear opening statement, followed by pricing and a bullet list of included features. Every sentence adds value, though the pricing details could be seen as secondary. The structure is front-loaded and easy to parse.

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 complexity (premium audit with multiple deliverables) and the lack of an output schema, the description adequately lists what the tool returns (recommendations, guide, competitive analysis, score estimates). It does not specify the return format (e.g., JSON or text), but for a complex tool the level of detail is 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?

Schema description coverage is 100%, so baseline is 3. The description does not add any information about parameters, their formats, or relationships. It focuses on the tool's purpose and outputs rather than parameter usage. No extra value beyond the schema.

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 identifies it as a 'Premium AEO audit' and indicates it includes everything from the sibling tool 'audit_domain' plus additional features. The purpose is clear, though it could be more explicit about the action (e.g., 'Perform a premium audit'). It effectively distinguishes itself from siblings by specifying the premium nature.

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 by comparing to 'audit_domain' (basic vs premium), but does not explicitly state when to use this tool versus alternatives like 'quick_check' or 'suggest_queries'. No clear when-not or alternative guidance beyond the cost hint. Context is present but not fully 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 and openWorldHint. The description adds the 'single-query' scope, which is useful, but it does not disclose return format, provider behavior, or other behavioral details. No contradictions with 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?

One sentence of seven words, front-loaded with the core purpose. Every word earns its place, and there is no redundant phrasing or unnecessary detail.

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 3-param tool with no output schema, the description is minimally sufficient but leaves gaps: it doesn't describe the response format, provider selection implications, or how this differs from audit_domain. It is adequate but not comprehensive.

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 descriptions cover domain and query, while provider has only enum values with no description. The tool description does not mention provider or explain defaults, so it doesn't compensate for the missing provider description. However, the enum values (exa, perplexity) are self-explanatory.

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: 'Quick single-query AI visibility check for a domain.' This distinguishes it from siblings like audit_domain (comprehensive audit) and suggest_queries (query generation), making the purpose unambiguous.

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 'quick' and 'single-query' wording implies it is for lightweight, focused checks rather than full audits, but it does not explicitly say when to use this tool instead of audit_domain or audit_domain_premium, nor does it offer exclusions or alternative recommendations.

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, so the agent knows this is safe and repeatable. The description adds minimal behavioral context beyond 'generate queries', suggesting it returns queries rather than performing an audit, but provides no details about rate limits, response format, or side effects. The description does not contradict 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 sentence, front-loaded with the action ('Generate AEO audit queries') and scope ('for a domain/industry'). Every word earns its place; there is no fluff or repetition. It is concise and well-structured for quick scanning.

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 has 4 parameters, no output schema, and no parameter descriptions, the description is under-specified. It does not explain what the generated queries look like, how count/language affect results, or how it differs from the sibling audit tools. The read-only annotations cover safety, but the description leaves significant gaps for an agent to invoke 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?

With schema description coverage at 0%, the description must explain parameter meanings. It only covers 'domain/industry' implicitly, leaving 'count' and 'language' unexplained. The schema's constraints (count min/max, language enum) are not referenced, so the description adds only a partial bridge between parameters and intent.

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: 'Generate AEO audit queries for a domain/industry.' It uses a specific verb ('generate') and identifies the resource (AEO audit queries). It distinguishes itself from sibling tools like audit_domain and audit_domain_premium by implying it produces queries rather than conducting audits, 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 provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or scenarios where this tool is preferred over audit_domain or quick_check. The usage context is only implied by the tool's name and purpose.

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