search_read

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

With no annotations, the description carries the full burden and does so: it discloses the billing rule ("Charged only if at least one page was read"), the unit price ($0.005 USDC per call), p99 latency of 15000ms, the source restriction to Wikipedia/news, and the return shape. It also explains the value proposition (replaces one search plus several page reads), which tells an agent this is a compound call rather than a raw search.

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?

It is front-loaded with the primary use case and disambiguating alternative before any parameter detail, and each sentence carries information. The trailing parameter enumeration is somewhat dense and partially restates the schema, but it is justified by 0% schema coverage; still, the run-on param list slightly hurts readability.

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?

No output schema exists, so the description supplies the return format (Markdown pages with title, URL, snippet, 1-5 of them). Combined with cost, latency, source scope, and the count/max_chars controls that shape the response size, an agent has everything needed to call this correctly and predict the payload.

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 does: query (required), source ('web' default or 'news'), count (1 to 5, default 3), max_chars per page (500 to 20000, default 4000) are all enumerated with their ranges and defaults. Only max_chars' effect is left implicit, but its name and range make the meaning clear.

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 concrete verb+resource and states exactly what the tool returns: top 1-5 result pages already read as clean Markdown with title, URL and snippet, sourced from Wikipedia or recent news. It distinguishes itself from siblings explicitly ("Not a general web search engine", "If links and a short summary are enough, web-search is cheaper"), so an agent can separate it from web_search, news_search, and webpage_reader without opening a 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?

It states the triggering condition ("Answer a question when you have no URL yet"), the exclusion (not a general web search engine), and names the cheaper alternative plus the condition that selects it (links + short summary is enough → web-search). This is the when/when-not/alternative triad stated outright.

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