AEO Auditing

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so repeating 'zero state mutation' earns nothing. However, the description adds genuinely useful facts not in the annotations: public unauthenticated access and a concrete rate limit of 60 requests/min per IP, plus a sketch of the return shape. That is real added context for an open-world network call.

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?

Purpose is front-loaded and the sentence ordering (purpose → usage → params → side effects → returns) is sensible. But the 'when you specifically need to execute audit_domain on AEO Auditor (aeoauditing.com)' clause and the 'Strictly read-only, idempotent... zero state mutation' clause largely duplicate the annotations and the tool name, so several sentences do not fully earn their 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 single-parameter read-only audit with no output schema, the description covers purpose, the sibling boundary, the required parameter, auth/rate-limit constraints, and the shape of the response. What is thin is depth-of-audit and failure behavior (e.g. what happens on an unreachable domain or how many checks run), which for an open-world network tool is a minor remaining gap.

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?

There is only one parameter and schema description coverage is 100%, with the schema already giving examples ('stripe.com' or 'https://stripe.com'). The description only restates 'url (required)', adding no further semantics such as whether subpaths/schemes are honored or normalization behavior, so baseline 3 applies.

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 first sentence gives a concrete verb ('Execute a ... diagnostic audit') and a specific resource ('any domain or URL'), enumerating the audit dimensions (AEO, GEO, JSON-LD Schema AST, /llms.txt readiness). It names both siblings, so the tool is distinguishable, though the later line 'Call this tool when you specifically need to execute audit_domain' is a tautological restatement that adds nothing.

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 has an explicit 'when to use' / 'do NOT use' frame and names both alternatives, but the routing content is hollow: 'use get_domain_benchmark or validate_robots_txt for their respective operations' never says which condition selects which sibling, and 'when you specifically need to execute audit_domain' is circular. The agent must infer the boundaries from the audit dimensions listed in sentence one.

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 read-only, idempotent, open-world, and non-destructive behavior, so the description is not solely responsible for those traits. It adds useful operational context beyond annotations: public unauthenticated access and a rate limit of 60 requests/min per IP, plus a high-level return shape.

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 front-loaded with the core purpose and structured with labeled behavior and return sections. Some space is wasted on the tautological when-to-use sentence, but overall it remains efficient and readable.

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 lookup tool with full schema coverage and rich annotations, the description covers both query modes, access/auth expectations, rate limits, and the general return shape. Although there is no output schema, the high-level return description is sufficient 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?

Schema description coverage is 100%, and both optional parameters are already documented with examples in the schema. The description only lists 'domain (optional), category (optional)' without adding meaning beyond what the schema provides, so the baseline 3 applies.

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 and resource: looking up a domain's AEO readiness benchmark score with a 4-pillar breakdown, or querying the industry leaderboard directory. It also names sibling tools, making the tool's scope distinguishable from audit_domain and validate_robots_txt.

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 when not to use the tool and names the sibling alternatives, which is useful. However, the positive usage guidance is circular ("Call this tool when you specifically need to execute 'get_domain_benchmark'") rather than stating the actual condition or preference that should select this tool.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is pre-covered; the description nonetheless adds genuinely new facts: public unauthenticated access and a 60 requests/min per IP rate limit. It also sketches the return shape, though it does not say what happens when both optional inputs are omitted or which input wins if both are supplied.

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 opening sentence is strong and front-loaded, and the rate-limit/return details earn their place. But the middle section is template boilerplate that restates the tool name as its own justification and pads the response with a generic 'structured JSON object containing status...' sentence, diluting an otherwise tight definition.

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?

With no output schema, the description usefully covers the return shape, auth model, rate limits and the alternative tools, which is enough for an agent to invoke it correctly. The only gap is the lack of guidance on the two optional inputs being mutually exclusive or one being required in practice.

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 both parameters are already documented with examples in the schema, which sets the baseline at 3. The description only restates that both are optional and adds no conflict-resolution or precedence semantics 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?

States a specific verb and resource (validate a robots.txt file or live domain robots.txt) and names the exact target set — 10 named AI crawlers including GPTBot, PerplexityBot and ClaudeBot — plus the generated compliant config. An agent can tell this apart from a general domain audit from the first sentence alone.

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 names the two siblings, 'audit_domain' and 'get_domain_benchmark', in a do-not-use clause, which is real routing guidance. However the positive 'when to use' clause is circular filler ('Call this tool when you specifically need to execute validate_robots_txt') and it never says how to choose between the domain and robotsTxtContent inputs, so it stops short of full when/when-not coverage.

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