web_search

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

With no annotations, the description carries the full behavioral burden, and it excels: it discloses per-attempt timeout, one retry on transient failures, the merging/dedup behavior, source tagging, and the _meta audit trail with provider(s), latency, and per-attempt details. This is far beyond typical descriptions and leaves little about execution behavior hidden.

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 description is dense but well-structured, front-loading the core purpose before the strategy details. Every clause contributes useful context—providers, strategies, retries, result shape, and metadata—without redundancy or filler.

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?

Given there is no output schema, the description appropriately documents the normalized result shape { title, url, snippet, content?, published_date?, source? } and the _meta structure. It covers provider selection, strategy behavior, timeout, retry, and output format, making the tool fully understandable for an agent even without inspecting schema definitions.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: it clarifies what fallback versus aggregate actually do, that results are deduplicated by URL, and that each result is tagged with its source provider. These details enrich the strategy and providers parameters beyond their terse schema descriptions.

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 description opens with a specific verb and resource, 'Search the web,' and immediately distinguishes this tool from the sibling provider_status by focusing on web search rather than status inspection. It also identifies the provider ecosystem (Kimi, MiMo, StepFun, Zhipu GLM), making the tool's scope 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?

The description gives clear strategic context: fallback is for trying providers in priority order until one succeeds, while aggregate is for parallel queries with merged results. It also explains that provider availability depends on configuration and API keys. It does not explicitly name provider_status as the alternative, so no exclusion guidance, but the intended usage is clear.

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