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

With no annotations provided, the description carries the full burden, and it delivers: it discloses result deduplication by URL, reciprocal-rank fusion, per-engine rank attribution, the $0.05/call cost, and the web-only limitation. This goes well beyond a generic tool description, though a mention of error behaviors or rate limits would have pushed it higher.

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 is front-loaded in a clear opening sentence, but the parameter list is a run-on that mixes periods, semicolons, and colons awkwardly: 'Params — q: search query; engines: comma list of 2-3 engines: yahoo, yandex (web mode). news mode has a single live engine (bing), so multi-engine is web-only; num_results: ...' The news-mode note is embedded mid-list, making it harder to parse than a clean structured list would be.

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 tool with no output schema and no annotations, the description covers a lot: what it does, why to use it, all parameters with formats, cost, and limitations. The main missing piece is a description of the return format (what a merged/deduplicated result set looks like), which would help an agent interpret the output without an output schema.

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?

The schema is essentially opaque (a single nullable 'params' object with additionalProperties: true and 0% coverage), so the description must compensate. It lists all seven keys (q, engines, num_results, region, timelimit, safesearch, mode) with types, constraints (e.g., 'cap 25', 'on|moderate|off'), and a concrete example. A brief note on the exact engine enumeration (whether Brave is a valid engines value, given the first sentence mentions it but the engines list only shows 'yahoo,yandex') is the main gap.

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 states a specific verb ('search'), a resource ('web'), and a distinguishing mechanism ('fanned out across 2-3 search engines (Brave, Yahoo, Yandex)... merged by reciprocal-rank fusion'). It clearly differentiates from sibling tools like serp (presumably single-engine) by emphasizing the multi-engine metasearch approach, and the name itself (serp_multi vs serp/serp_batch) reinforces the distinction.

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 provides a rationale for when to use it ('consensus ranking across engines instead of one engine's bias') and a caveat on when not to ('news mode has a single live engine (bing), so multi-engine is web-only'). However, it never explicitly compares against serp, serp_batch, or serp_read (e.g., 'use this instead of serp for broader coverage'), leaving some selection guidance implicit.

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