web-search

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds the markdown output format, which is useful, but says nothing about live-fetch caching, truncation, or the LLM-extraction path described in the schema.

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 sentences, zero waste, with the core action front-loaded before the return format. Nothing extraneous.

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 rich annotations, a fully documented 6-parameter schema, and no output schema, the definition covers what an agent needs to invoke it. The one gap is not routing between this tool and its sibling search_web_pages.

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 every parameter is already documented with examples, defaults, and constraints. The description adds no parameter-level information beyond the schema, so the baseline of 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?

States a specific verb and resource: 'Fetch and extract content from a web page,' and adds the return format (markdown). It is clearly distinguishable from the sibling search_web_pages by the fetch-vs-search verb, though it never names the sibling explicitly.

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 -- fetch when you have a URL -- but the description gives no explicit when-to-use guidance, no condition that selects it over search_web_pages, and no prerequisite or caveat language.

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 and non-destructive, so the safety profile is covered. The description adds real behavioral context about the pro/realtime quality-latency tradeoff, but says nothing about rate limits, auth, result freshness guarantees, or response shape beyond 'snippets'.

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 purpose and preference statement, then organized into short tips for querying, filtering and mode selection. Each block earns its place, though a couple of clauses duplicate what the schema already spells out.

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 13-parameter read-only search tool with no output schema, the description covers query crafting, filtering, and mode selection well enough to call it correctly. The remaining gap is routing versus fetch_page_content, which the description never mentions.

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 every parameter is already documented at the field level, including the subtle query_time vs. published_after distinction. The description's query-writing tip ('describe the ideal page, not keywords') and filter callouts largely restate the schema, so it adds only marginal value above the 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?

The description states a clear verb and resource ('search tool' returning 'relevant results with snippets for any query') and positions itself against a built-in web search. It does not, however, distinguish itself from its actual sibling fetch_page_content (search-for-unknown vs. fetch-a-known-URL), so an agent must infer that split.

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 gives concrete conditions to reach for it ('current events, recent data, and information beyond your knowledge cutoff') and explains when to pick each mode ('pro' default vs. 'realtime' for latency-sensitive tasks). What's missing is an explicit when-not branch pointing at fetch_page_content when the agent already has a URL.

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