deepseek_search

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds the 128-character native query limit, which is genuinely behavioral, but says nothing about retries (despite the request_budget param), caching, or how need_content/force_refresh change behavior.

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 tight sentences with the core purpose front-loaded, then syntax support, then the length constraint and routing hint. No filler, though the operator list is dense enough that a second read is needed to map operators to parameters.

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 16-parameter tool with 19% schema coverage and no output schema, the description leaves most of the surface undocumented — notably the boolean/output-shaping params (need_content, force_refresh, max_characters, request_budget) and additional_queries. An agent can form a basic query but cannot confidently use the majority of the tool's capabilities.

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 only 19%, so the description must compensate, and it partially does by mapping operator syntax to parameters (site:/-site: → include/exclude domains, after:/before: → date range, quotes/OR → query semantics). However, roughly ten parameters (count, max_results, need_content, force_refresh, localization, ori_question, additional_queries, include_text/exclude_text, max_characters) get no explanation of purpose or interaction.

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+resource ('DeepSeek native web search') and the query syntax it supports, which sets it apart from deepseek_fetch/deepseek_extract as a query-based search tool. It does not explicitly name those siblings, but the resource is unmistakable.

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 a concrete switching rule: native queries are capped at 128 Unicode characters, so use 'advanced' for longer queries and filters. That is a clear when-to-use-this-vs-other condition, though it references a tool not present in the sibling list and never mentions when to prefer deepseek_fetch or deepseek_extract.

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