AEO Scanner

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

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds significant behavioral context: payment model ($1.00 per call via x402), output structure (per-check scores, AI Identity Card, business profile), and behavior on payment_required (returns x402 payload). There is no contradiction 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?

The description is relatively long but front-loaded with the main function. It is well-structured: main purpose first, then specific categories, exclusions, and payment details. Some repetition or excessive detail could be trimmed, but overall it earns its length given the tool's complexity.

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 (67+ checks, 12 categories, payment system) and absence of an output schema, the description thoroughly covers the output content and behavior. It includes what the tool does and does not do, payment flow, and error handling (payment_required). No significant 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 description coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the categories parameter in detail (e.g., GEO checks include specific citation signals, Agent Readiness covers specific standards). This enriches understanding of param values.

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 performs a 'Full AI visibility audit across 67+ checks in 12 categories' and differentiates from sibling tools by explicitly stating it does not generate fix code (use fix_site) and can be used for benchmarking (use compare_sites). The verb and resource are specific, and the scope is well-defined.

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 explicit guidance on when not to use the tool (e.g., for fix generation) and directs to alternatives (fix_site, compare_sites). However, it does not address usage relative to scan_site, another sibling tool, which could be a gap. The payment and x402 details also inform usage context.

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?

Beyond annotations (readOnlyHint, openWorldHint), the description discloses payment details ($3.00 via x402), concurrent scanning behavior, and specific outputs (fix code, projected scores). 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?

The description is a single paragraph that packs essential information without excess. It is front-loaded with the main purpose and structured logically. Could be slightly more structured (e.g., bullet points) but remains effective.

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 no output schema, the description adequately details the key outputs (scores, winners, gaps, fix code, projected scores) and payment behavior. It covers the major aspects needed for an AI agent to use the tool, though error handling or rate limits are not mentioned.

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% with clear parameter descriptions. The description does not add additional meaning beyond the schema, providing no new insights into parameter usage or formatting. Baseline of 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 clearly identifies the tool as a competitive gap analysis that scans two sites concurrently and provides side-by-side scores, category winners, gaps, and generated fix code. It distinctly distinguishes itself from sibling tools like scan_site (single site) and audit_site.

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 states when to use: benchmarking against a competitor or when scan_site detects competitors. Provides payment context. Lacks explicit exclusions for when not to use, but the guidance is clear and actionable.

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 only have openWorldHint: true, which is consistent with the description detailing payment ($5.00 via x402) and generative behavior. The description fully discloses the paid nature, output type, and conditional payment_required response, adding significant value beyond 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 paragraph that front-loads the main purpose, then details outputs, usage guidance, and payment info. It is reasonably concise without wasted words, but could benefit from structured formatting like bullet points for readability.

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?

Covers all essential aspects: what it does, outputs, prerequisite, payment details, and behavior on payment_required. Lacks mention of error handling or invalid URL scenarios, but overall complete given the tool's complexity and schema richness.

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% with good descriptions for url, pages, and format. The description does not add additional meaning or context beyond what's in the schema, 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 clearly states the tool generates fix code for AI visibility issues across multiple areas (AEO, GEO, Agent Readiness) and lists specific outputs like schema generation, robots.txt, etc. It distinguishes from sibling scan_site by recommending to run scan_site first.

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?

Provides clear prerequisite: 'Run scan_site first to see which issues exist.' Also explains payment flow and behavior on payment_required. However, it does not explicitly say when to avoid this tool or compare to other siblings like audit_site or compare_sites.

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 (readOnlyHint=true, openWorldHint=true) indicate a safe, read-only tool. The description adds valuable behavioral context: it's free, no API key needed, returns specific scores and an AI Identity Card, and covers 67+ checks across 12 categories. It also clarifies what it does not return (per-check details or fix code), further setting 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 fairly concise and front-loaded with purpose. It packs substantial information (scores, what's included, what's not, alternatives) into a few sentences. While dense, it avoids unnecessary words. A more structured format (e.g., bullet points) could improve readability, but it is effective.

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 simple parameters (2, with 1 required), annotations (readOnly, openWorld), and no output schema, the description is complete. It clearly states what the tool returns (scores, AI Identity Card, competitors, business profile, top issues) and its limitations (no per-check details or fix code), directing to siblings for deeper analysis.

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 the parameter schema already documents both parameters. The description adds meaning beyond the schema by explaining the tool's output (the scores and their ranges, AI Identity Card, etc.), which helps the agent understand the impact of parameters like 'pages'. It enriches the context without directly describing parameters.

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's a 'Quick AI visibility scan' and lists the specific scores (AEO, GEO, Agent Readiness) and other outputs (AI Identity Card, competitors, etc.). It distinguishes from siblings by explicitly stating what it does NOT return and directing to audit_site, fix_site, and compare_sites for those needs.

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 explicit guidance on when to use this tool vs alternatives: 'Does NOT return per-check details or fix code — use audit_site for full breakdown, fix_site for generated fixes, compare_sites to benchmark against a competitor.' This clearly states when not to use and what to use instead.

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