Keenable Web Search

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by specifying the return format (markdown), which is not in the annotations. It does not mention caching/live behavior or LLM extraction, but those are documented in the input schema. No contradiction with annotations.

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 two concise sentences: the first states the core action, the second states the output format. There is no redundant or filler content; every sentence earns its 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?

Given the tool's complexity (4 params, no output schema), the description provides the essential context: purpose and output format. Annotations and schema handle safety and parameter details. It does not explain potential caching behavior or edge cases, but these are not critical for a read-only fetch tool and are partially covered by the 'live' parameter description.

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 all four parameters having descriptive text. The tool description adds no parameter-specific meaning beyond the schema, so the baseline score of 3 applies. It does not compensate for any gaps because there are none.

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 specific verbs ('Fetch and extract') and identifies the resource ('content from a web page'), clearly distinguishing it from the sibling tool 'search_web_pages' (search vs. fetch specific page). It also mentions the output format (markdown), which further clarifies purpose.

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: you would use this tool when you have a specific URL and want its content. However, it does not explicitly state when to prefer this over search_web_pages or provide exclusions/alternatives. The usage context is clear but not explicitly differentiated from the sibling 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?

The annotations already establish readOnly, openWorld, idempotent, and non-destructive behavior. The description adds useful operational behavior beyond those: it returns snippets, supports pro vs realtime modes, supports date and site filtering, and frames realtime as latency-oriented. It does not mention rate limits or pagination, but nothing contradicts the annotations.

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: the default role and core return behavior come first, followed by concise tips. Every sentence earns its place, and it packs substantial guidance into only a few lines without 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 content-rich search tool with 10 parameters and no output schema, the description covers the main return promise ('relevant results with snippets'), suggests filters, and explains modes. It does not detail result shape or pagination, and it could more explicitly point to fetch_page_content as the natural next step, but it is still adequate for confident invocation.

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 documents all parameters. The description adds strategy-level value beyond the schema, such as describing the ideal page rather than keywords, giving a concrete query example, and explaining when realtime mode is preferable. This is genuinely helpful for correct parameter use.

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 explicitly identifies this as a web search tool: 'Your default search tool' that 'Returns relevant results with snippets for any query.' It is clearly distinguished from the sibling fetch_page_content by framing itself as search-over-fetch, and it names its role relative to built-in web search.

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 gives concrete when-to-use guidance: current events, recent data, and information beyond the knowledge cutoff. It also states a preference over built-in web search and provides actionable query and mode-selection advice. It does not explicitly mention fetch_page_content as the complementary follow-up, but the intended context is clear.

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