SearchBlueprint

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds that two separate surfaces (AI Overview and AI Mode) are queried, but it says nothing about freshness or caching, latency/cost of an external SERP call, or whether the two surfaces are reported separately or merged.

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 naming the action, the target surfaces, and the two inputs, with no filler. Nothing could be cut without losing meaning.

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 and no parameter documentation, so the description carries most of the burden. It does convey the essence of the answer (presence versus citation) and names both surveyed surfaces, but it leaves the return shape, the meaning of the country default, and result freshness 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 description coverage is 0%, so the description must compensate, and it only implicitly covers 'domain' and 'keyword'. The 'country' parameter, including the default 'us' and how it affects geo-specific AI Overview results, is not mentioned anywhere and is therefore undocumented in both places.

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 gives a specific verb ('Check') and a precise resource ('Google AI Overview and AI Mode'), and states that it answers whether a domain 'appears in / is cited by' the surface for a keyword. This distinguishes it from the sibling rank_check, which suggests a classic ranking lookup, though it does not directly name that sibling.

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?

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The agent must infer from the verb 'Check' that this is a point-in-time lookup, and nothing says when rank_check or page_meta would be the better choice.

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 covered. The description adds that the tool returns title, meta description, H1 and headings, but does not cover redirects, auth requirements, rate limits, or error behavior.

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 definition is a single short sentence with no redundant wording, and the key information is front-loaded. Every word contributes to describing what is fetched.

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 rich annotations this is close, and the description lists the metadata fields returned. However, with no output schema, it does not explain the response structure, heading format, missing-metadata behavior, or failure modes.

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 0%, and the only parameter is an undocumented string named url. The description mentions "a URL's" but adds no format constraints, redirect handling, encoding requirements, or other semantics beyond the obvious parameter name.

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 gives a specific verb ("Fetch") and resource ("a URL's title, meta description, H1 and headings"), so the tool's purpose is clear. It does not differentiate this tool from siblings like ai_presence or rank_check, but the core operation is unambiguous.

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 no when-to-use guidance, no exclusions, and no mention of alternatives such as ai_presence or rank_check. Usage is only implied by the purpose statement.

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 cover read-only, idempotent, open-world and non-destructive behavior, so the bar is lower. The description adds two useful non-annotation facts: the lookup is 'live' (real-time query) and that 0 is a sentinel meaning 'not in top 100' — important since there is no output schema to convey it.

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?

One front-loaded sentence with the resource and scale up front and the edge-case sentinel tucked into a parenthetical. No filler.

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 does cover the return value (position, 0 = not in top 100), which is the most important gap filled. But for a 3-parameter tool it leaves the country dimension and domain/keyword input conventions entirely to a mostly empty schema.

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 only 33% — domain and keyword are bare strings and country is the only documented parameter (sg|us|uk|au|my, default us). The description loosely maps domain and keyword but says nothing about domain format (protocol, subdomain, path), how keyword matching works, or what country does and that it defaults to us.

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 concrete verb+resource (get a domain's live Google organic position for a keyword) and defines the result scale. It does not mention the siblings ai_presence or page_meta, so differentiation must be inferred from the resource names.

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: call it when you want a rank for one domain/keyword pair. There is no explicit when-not guidance (e.g., bulk checks, non-Google engines, or the adjacent presence/meta siblings), and nothing about cost or rate limits despite 'live' implying a real-time lookup.

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