knowngood

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states that tools are listed, never called; that it reads only the named site plus published population figures; that it does not consult the index; and that running it changes no ranking or listing. It also clarifies that could_not_ask is a distinct answer and never reported as a no.

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 dense but well-structured: it front-loads the core action and then adds return-value semantics, safety constraints, and scope. Each sentence contributes meaningful information, though it could be tightened slightly by removing redundant phrasing like 'published population figures'.

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 tool with a single well-documented parameter and no output schema, the description is remarkably complete. It enumerates all possible return values, explains the meaning of the ambiguous 'could_not_ask' result, and states side-effect and scope constraints, giving an agent everything needed to call and interpret the tool 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?

The input schema already describes the single url parameter and its format, including that https is assumed. The description adds general context about checking the site live but does not provide significant additional parameter-level detail. With 100% schema description coverage, 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 opens with a specific verb and resource: 'Check a website LIVE for WebMCP tools' and further specifies whether the tool actually registers when the page runs. It clearly differentiates itself from index-based lookups by stating it does not consult the index, which helps distinguish it from siblings like get_site_report.

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 context: it is for live website checks rather than index consultation, and it explains what happens when robots.txt refuses AI input. However, it does not explicitly mention when to choose this tool over find_capability or get_site_report, nor does it state exclusions.

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?

With no annotations, the description carries the behavioral transparency burden. It does well by distinguishing probe-verified signals from unverified apparent actions, explaining verification tiers and discovery sources, and explicitly describing empty-result behavior with 'never a nearest guess.' It does not mention auth, rate limits, or read-only status, but the behavioral semantics of the results are unusually well disclosed.

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 compact and front-loaded with the core purpose. Every sentence adds value: the first declares what the tool does, the second enumerates return contents, and the third clarifies empty-result behavior. There is no filler or 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?

The description is reasonably complete for a search tool: it states the output fields, explains how results are verified or unverified, and specifies the empty result behavior. It does not cover interpretation of verification tiers or explicit guidance on composing filter parameters, but those are partly addressed by the schema. Without an output schema, the description does enough to set correct expectations.

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 high (~78-89%), and most parameters already have detailed descriptions in the schema. The tool description itself does not add parameter-level meaning beyond the schema. Per the baseline for high coverage, a 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 uses a specific verb-resource pair: 'Find websites where an agent can accomplish a task.' It clearly describes what the tool returns, including agent-readiness signals, verification tier, and discovery method. It does not explicitly name or contrast the sibling get_site_report, so differentiation is implied rather than stated.

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 when to use the tool: when you want to discover sites where an agent can accomplish a task. It does not mention alternatives, when not to use it, or how it relates to get_site_report. The usage context is clear but no exclusions or alternative routing are provided.

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?

With no annotations, the description carries the full burden and does well: it discloses that unmatched hosts return found:false, that it never guesses a nearest match, and that the report has a date and URL to cite. Read-only behavior is implied but not harmful; the 'apparently' also clarifies that reported capabilities are indicative rather than guaranteed.

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 information-dense with no filler: it defines the resource, lists the fields, states the core question it answers, details the not-found behavior, and gives an output instruction. Every clause earns its place and the purpose 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?

For a simple one-parameter read tool with no output schema and no annotations, the description fully equips an agent: what it fetches, what the report contains, what it returns for misses, and how to cite it. Nothing essential for correct invocation 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?

Schema coverage is 100% and the only parameter, host, already has a clear description including an example. The tool description adds minimal parameter-specific meaning beyond 'one listed website', so the schema does the heavy lifting; a 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?

States a specific verb, resource, and outcome: fetching a 'dated verification report' for a single listed website and answering whether that specific host is agent-ready. The description enumerates the report's contents and distinguishes itself from merely finding capabilities by framing the question as 'is this specific host agent-ready?'.

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 a clear use case: 'Answers is this specific host agent-ready?' and scopes input to one listed website. It doesn't explicitly contrast with find_capability or state when to choose that sibling, but the single-host versus capability-search distinction is strongly implied by the wording.

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