WebAudits: Performance & GEO Diagnostics

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 covered. The description adds the analysis scope and what it recommends, but says nothing about fetch behavior, timeouts, or how the URL is retrieved, leaving meaningful behavioral gaps.

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 tight sentences, front-loaded with verb+resource, followed by the concrete metrics reported and the remediation suggestions. No wasted words and every clause carries 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?

With no output schema, the description carries the return-value burden and does so by naming the four metrics and the recommendation content. It's nearly complete for a read-only audit, though it omits any note on how or when the URL is fetched.

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 url and response_format are fully documented in the schema, and the enum makes the format choice self-explanatory. The description adds no format syntax or semantic detail beyond the schema baseline.

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 (Analyzes) and resource (HTML tree structure) and enumerates concrete outputs (DOM node count, maximum depth, div ratio, Lighthouse threshold violations). This is specific enough to naturally distinguish it from audit_geo_readiness and audit_lcp_trace without needing to name them.

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?

No when-to-use guidance, no conditions for choosing this over the sibling audit tools, and no exclusions or prerequisites. The only context clue is 'public URL,' which hints at the input requirement but not usage.

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 readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds real value by disclosing exactly which external resources are fetched (robots.txt and /llms.txt), though it omits fetch failure/timeout behavior and whether results are cached.

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?

A single front-loaded sentence with zero filler: the inspection targets are stated before the rationale, and nothing is repeated from the schema or title.

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 should hint at what the diagnostic returns (e.g. per-crawler allow/deny plus llms.txt presence), but it only implies a report via the response_format enum. For a simple read-only tool this is adequate but leaves the result shape unspecified.

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 url (with protocol) and the markdown/json response_format are fully documented in the schema. The description mentions no parameter and adds no syntax or format detail beyond it, 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 names a concrete verb ('Inspects') and two specific resources (robots.txt AI-crawler rules and /llms.txt), which concretely defines the jargon name 'GEO readiness'. The AI-crawler focus cleanly separates it from the sibling DOM/LCP audits.

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?

Usage is only implied by the audit-family naming; the description never states when to reach for this audit versus audit_dom_bloat or audit_lcp_trace, nor any prerequisites (e.g. the site must be publicly reachable). No exclusions or alternatives are given.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds what is inspected but says nothing about the live network fetch, timeouts, mobile emulation behavior, or repeatability cost that an agent might care about for an open-world probe.

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?

A single dense sentence with no filler, and the primary measurement (server response time / TTFB) is front-loaded before the secondary LCP inspection. It earns its length but is slightly packed.

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 read-only, two-parameter tool with full schema coverage and no output schema, the description covers the measurement scope adequately. It still leaves gaps: no indication of relationship to sibling audit tools, no mention of whether the target must be publicly reachable, and no hint about what the markdown/json output contains.

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 only two params, both fully documented in the schema (URL with protocol, response_format enum). The description adds no parameter-level detail beyond the schema, 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 names concrete measurements (TTFB, HTML weight, mobile LCP delay causes like lazy-loaded hero images) with a specific verb ('Measures'/'inspects'), so the agent knows exactly what this tool returns. It does not, however, contrast itself against siblings like audit_dom_bloat or audit_geo_readiness, so differentiation is left to inference from topic.

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?

Usage is implied by the description (use it when you want server response time and mobile LCP diagnostics), but there is no explicit when-to-use, when-not-to-use, or alternative-routing statement pointing at the sibling audit tools.

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