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

Goes well beyond the readOnly/destructive annotations: result cap of ten, relevance ordering, that excerpts are search-engine text rather than verified quotes, and an explicit prompt-injection warning that page text is publisher-written and never an instruction. The only tension is that annotations declare openWorldHint=false while the tool searches the public web, which the description does not reconcile.

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?

Four compact sentences, all load-bearing, front-loaded with capability and output shape before the caution. Only the prompt-injection sentence could be trimmed slightly, but it earns its place for a web-content tool.

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?

Output schema exists, yet the description still usefully summarizes the return tuple and the citation workflow. What it omits is parameter-level guidance and any indication of what companyId does, which leaves a real gap for a 2-parameter tool with 50% schema coverage.

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?

At 50% schema coverage neither parameter is meaningfully explained: the description never mentions the query string, its 2-400 character limit, or search syntax, and says nothing about the companyId wrapper despite a web search plausibly being scoped to a company. The one schema description present ("UUID value wrapper") carries no semantic weight either.

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?

Specific verb + resource ("Searches the public web") plus the exact return shape (up to ten pages, best first: title, URL, date, excerpt). It implicitly separates itself from the read-the-full-page sibling by describing short result payloads, so an agent can tell the two apart immediately.

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?

States the concrete discovery use cases (firm bio, writing, interviews, portfolio announcements, news) and explicitly routes to fundraising_read_web_page as the follow-up before citing. That is both a when-to-use and an alternative-naming, with no inference required.

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