DeepSeek Web Search

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds real value beyond them: the shape of each result, the size of the summary field, the cost implication of needContent (responses become much larger), and supported query operators. It stops short of pagination or rate-limit behavior, which is a minor gap.

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?

Three dense sentences, front-loaded with purpose and return shape, then operators, then the summary-vs-content tradeoff. No filler, no restatement of the title, and the most decision-relevant constraint (summary is usually enough) lands where an agent will read it.

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?

There is no output schema, so the description must carry return-value information, and it does so by listing result fields and summary length. It omits any note on count limits or the role of oriQuestion/query length, though those are documented in the schema, so the definition is nearly complete for a four-parameter search tool.

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 the baseline is 3. The description goes beyond the schema by enumerating the query operator syntax (site:, -site:, lang:, after:, before:, quoted phrases) and by giving decision guidance for needContent ('only when you truly need page bodies'), which the schema only describes as making responses larger.

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 (search) and resource (the web/tool owner: DeepSeek Web Search) and enumerates the returned fields (title, url, snippet, summary, date, authority), which is exactly what separates it from the sibling fetch tool. An agent can tell this is a query-and-rank tool rather than a URL-retrieval tool without opening any 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?

Gives an explicit when-not condition: enable needContent only when you truly need page bodies, plus the inference that summary (600-800 chars) is usually sufficient. It does not name the sibling tool fetch as the alternative for full-page retrieval, so routing between the two is left to inference rather than stated.

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