deepseek_search

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, so the safety profile is covered structurally. The description adds meaningful non-annotation context: a response cache that refresh bypasses, optional query rewriting via deepseek-flash, dedupe collapse behavior, and boilerplate stripping. It does not mention rate limits, cost, or failure/fallback behavior, keeping it below a 5.

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 purpose, primary-use statement, and sibling differentiation are front-loaded in three tight sentences, then a compact Args block. Every line earns its place, though the Args list at 16 entries makes the whole thing long; the leading prose could be trimmed slightly without loss.

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 this is thorough: ranking modifiers, content-vs-snippet mode, char budgets, domain filters, date filters, and cache control are all explained. An output schema exists, so return-value explanation is correctly omitted, and nothing an agent needs to invoke 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 bears the full burden, and it documents all 16 parameters with defaults, ranges, and formats (count 1-50 default 5, date formats YYYY-MM-DD/YYYY, query operators site:/after:/before:, example domain lists). This meaningfully exceeds what the bare schema conveys.

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?

The first sentence names a specific verb (search) and resource (web via DeepSeek index) plus the return shape (page text, snippets, metadata). It explicitly states 'Primary search and retrieval tool for AI agents' and contrasts itself with the deepseek_research sibling, so an agent can distinguish the two without inspecting schemas.

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?

It names a positive context ('Use for standard search, targeted queries, and discovery') and gives an explicit differentiation rule versus deepseek_research ('auto-fetches stub pages' vs 'only returns indexed content'). It stops short of naming when to prefer deepseek_fetch, deepseek_fetch_many, or deepseek_extract for known-URL retrieval, leaving some routing to inference.

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