deepseek_web_search

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

No annotations are provided, and the description carries the full load well: memory caching with a cached flag, deduped concurrent request sharing, local per-endpoint rate limiting with the rate_limited_local error code, an 8 MiB response_too_large failure mode, and rewrite being skipped when lang is set with silent fallback. These are exactly the operational traits an agent needs before invoking.

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?

The prose preamble is front-loaded and dense with useful content, but the trailing Args block restates the lang guidance almost verbatim ("For non-English queries set it to the appropriate code; without it results may be mixed-language. For named entities test with and without the operator"), which appears twice. Redundant rather than bloated, so minor deduction only.

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 10-parameter search tool with no annotations, the definition covers invocation semantics, cost/alternative tradeoffs, failure codes, and even result field meanings (date RFC 3339, authority 0-4 with -1 unknown). An output schema exists so return-value structure needn't be spelled out, and nothing needed to call it correctly is missing.

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: every one of the 10 parameters is documented with bounds (query max 128 chars, count 1-50 default 10), supported query operators (site:, -site:, "phrase", lang:, after:, before:), and defaults (dedupe on, rewrite off, refresh false). It also explains secondary effects, e.g. that dedupe causes extras to be requested upstream so duplicates don't leave you short.

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 ("Search the web with DeepSeek's index") and immediately states what comes back (titles, URLs, dates, authority and rerank scores). It also distinguishes itself from the sibling deepseek_fetch by positioning this tool as the discovery/ranking entry point, so an agent can pick it 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?

Explicitly says what to use it for ("discovery and ranking") and names the alternative plus the decision rule: set need_content=True to avoid "calling deepseek_fetch afterwards" because it is "cheaper and more reliable." It also gives conditional guidance for lang (non-English queries) and for named entities (test with and without the operator).

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