PageCritic

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

Annotations only say readOnlyHint and openWorldHint; the description adds substantial context beyond that: 30–90 second runtime, async behavior with status "running", free vs paid report boundaries, human payment at report_url, 24-hour same-language caching, rate limits, and API-key credit behavior. Nothing contradicts the read-only annotation.

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?

It is front-loaded with what the tool does and returns, then adds operational details. The pricing and API-key sentences are long, but they serve important behavioral transparency rather than repeating schema or annotation data.

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?

There is no output schema, but the description fully explains the return shape, async flow, rate limits, paid-report behavior, caching, and language effects. An agent has enough information to select and invoke the tool correctly without guessing.

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 the schema already explains both url and language. The description still adds useful semantics: language affects the report and cached results, "pt" yields Brazilian Portuguese, and a recently audited URL in the same language returns the same result.

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 (loads a public landing page in a real browser) and enumerates the exact outputs: conversion score, seven sub-scores, top issues, fixes, and fix_prompt. It also directly routes async results to get_audit_result, so an agent can distinguish this tool's role from at least that sibling without opening schemas.

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 names when to use it: pages not converting, pre-launch second opinions, competitor comparison. It also names exclusions (login-protected pages, non-HTML files, general SEO keyword research) and tells the agent to call get_audit_result when status is running.

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 declare readOnlyHint and openWorldHint; the description adds genuinely new operational context: plain HTTP fetches (not a headless browser), a 5-15 second runtime, free usage and a 15-checks-per-hour-per-client rate limit. It also enumerates which signals are probed and that findings come back with a 0-100 score and prioritized fixes.

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?

Front-loaded with the core action and the multi-bot probe list, then usage conditions, exclusions and cost in a compact final sentence. The crawl of bot names and artifacts is dense but each item is an actual output the agent may need to report; only the bot enumeration is longer than strictly necessary.

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?

There is no output schema, yet the description covers what is returned (blocked/challenged status per bot, robots.txt rules, visible text without JS, JSON-LD types, sitemap, Markdown, llms.txt, score, fixes), how it runs, and how long it takes. Nothing an agent needs in order to call this correctly is missing.

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?

Only one parameter and schema coverage is 100%, so the schema already carries the baseline (which would be 3). The description adds the constraint that the target must be a *public* page, which is meaningful eligibility information beyond the schema's format example, though it stops short of further URL validation details.

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?

Starts with a concrete verb (fetches) and names the exact resources and scope: a public page fetched as a normal browser plus six named AI crawler user-agents, then reports blocking, robots.txt rules, text visibility, JSON-LD, sitemap, Markdown, llms.txt and a 0-100 score. It explicitly contrasts itself with the sibling audit_landing_page, so an agent can separate this from design/copy auditing without opening either schema.

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?

Gives an explicit when-to-use trigger (someone asks whether ChatGPT, Claude or Perplexity can see or cite their site, or why the site doesn't appear in AI answers) and an explicit when-not-to-use with the named alternative (design or copy -> audit_landing_page). Nothing about the selection decision is left to inference.

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 openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the precondition that the audit must be running, and a polling cadence of ~20 seconds. It does not describe what happens if the audit is not running or has failed, which would have pushed this to a 5.

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?

Three short sentences, front-loaded with the purpose, followed by the precondition and polling guidance. Every sentence earns its place with no redundancy.

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 polling tool with no output schema, the description closes the important gaps: it states the return shape matches audit_landing_page and specifies the precondition and cadence. An agent has everything needed to call 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 the description adds no meaning beyond it – the format hint ('24-character audit_id') is already in the schema. Baseline 3 is correct when the schema carries the parameter documentation.

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+resource ('Returns the current result of an audit') and ties it to the originating sibling ('started with audit_landing_page, by its audit_id'), so an agent can distinguish it from that sibling 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?

Explicit when-to-use condition ('only when audit_landing_page returned status "running"') plus concrete operational guidance ('wait about 20 seconds between calls') and a named alternative tool. Nothing is left to inference.

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