full-web-search

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

With no annotations provided, the description carries the full behavioral burden. It does disclose a genuine behavioral trait: the tool performs a two-stage operation (search, then follow links to extract full page content), which tells the agent this is heavier than a plain search. However, it stops short of warning about the costs or failure modes of that behavior — latency, a slow underlying website, partial fetch successes, or content truncation — which an agent would benefit from knowing.

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?

Three short sentences, each of which earns its place: the first defines the action, the second states the positioning and mechanism, and the third gives the explicit alternative routing. The content is dense yet minimal, with the most important facts appearing in the first sentence.

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 moderately simple 4-parameter tool with rich schema coverage, the description provides the essential facts and points to the correct alternative. The main missing piece is absence of an expected latency/failure profile for the full-page extraction step — coverage that would be especially useful given the 'fetches full content' behavior and the format of results is not specified. Still, what's missing is the optional, not-basic, information, and the definition is arguably strong enough.

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 100%, so every parameter (query, limit, includeContent, maxContentLength) is already documented at the schema level with sensible defaults. The description adds no meaningful information about parameters while also requiring none because the structured definitions do the heavy lifting. Baseline 3 is appropriate.

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 states a specific verb and resource: 'Search the web and fetch complete page content from top results.' It further clarifies its mechanism by explaining it 'follows the resulting links to extract their full page content,' which unambiguously distinguishes it from siblings like get-web-search-summaries and get-single-web-page-content. An agent can understand exactly what this tool does without opening any other definition.

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 explicitly routes for the lightweight case: 'Use get-web-search-summaries for a lightweight alternative,' giving clear when-to-use guidance and naming the competing tool. It also positions itself as the right choice for comprehensive research. It does not, however, cover the case where a single known URL is already in hand and get-single-web-page-content should be used, so the exclusion guidance is slightly incomplete.

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