search_web

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

With no annotations, the description carries the full burden, and it discloses a real behavioral trait the schema cannot express: per-call pricing for each mode ($0.005 / $0.01 / $0.02). That is meaningful cost information an agent can act on. It still omits rate limits, auth requirements, and return-shape behavior, which keeps it from 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?

Two sentences, both front-loaded and dense with useful information; the mode list is the highest-value content and comes first, with pricing relegated to a second sentence. It is slightly run-on, but every clause 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?

For a 7-parameter, five-mode tool with no output schema, the description does the essential job of explaining what each mode returns (Markdown, AI answer, extracted JSON, HN stories). It does not differentiate from siblings like verify_fact or check_market, and gives no return-format constraints, but it is complete enough to call 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%, so every parameter (url, limit, query, schema, country, num_results) is already documented in the schema, including mode applicability. The description adds no parameter syntax or format detail beyond what the schema provides, so the baseline 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?

The description names a concrete verb ('search or read the live web') and then disambiguates all five modes with a distinct purpose each ('structured Google results', 'semantic/intent search with an AI-generated answer', 'main content as clean Markdown', 'structured data extracted per a JSON Schema', 'top Hacker News stories'). An agent can map a user intent to the correct `mode` value without opening the 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?

By enumerating each mode's behavior the description implicitly tells the agent which mode to pick for a given intent (e.g. want an AI answer -> search_semantic; want raw page text -> read_page). It does not, however, state any exclusions, prerequisites, or how to choose between overlapping modes like search_google vs search_semantic for plain keyword lookups.

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