deepseek_deep_research

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses the internal pipeline (subquery decomposition, concurrent retrieval, citation markers [1],[2]) and the caching behavior implied by the refresh parameter. It stops short of stating cost, latency, or failure modes for a tool that fans out multiple network calls, which is the one remaining 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?

Front-loaded with a one-line purpose, then usage rules, then a compact Args block. Every line carries information — no restatement of the tool name, no filler prose.

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?

An output schema exists, so return values needn't be explained, and the parameter section compensates fully for the 0% schema coverage. Purpose, routing, and per-argument semantics are all present for a 7-param tool, leaving nothing an agent would need to guess before calling it.

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 carry the full burden and it does: all seven params are documented with meaning, ranges (topic max 500 chars, max_queries 2-4, max_pages_per_query 1-5), defaults (3, 3, True, False, True), and an example value for lang ('en', 'pl'). This is information the schema alone does not convey.

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?

Opens with a specific verb+resource: 'Execute multi-angle research on a topic and generate a cited briefing report.' The second sentence explains the mechanism (decompose into subqueries, concurrent retrieval, synthesized cited report), which distinguishes it from the plain search/fetch siblings.

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?

Explicitly routes the agent: 'Use for deep topic synthesis. Do not use for simple lookups (use deepseek_search/deepseek_research) or reading known URLs (use deepseek_fetch).' Both exclusions and named alternatives are given, so nothing is left to inference.

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