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

Annotations already declare readOnly, idempotent, non-destructive. The description adds critical behavior beyond that: parameters go in the query string despite POST, JSON body not accepted, response includes `id` and `results[]` with only title/link/snippet, measured latency and size, and that no page text is returned. No contradiction with annotations.

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 every sentence carries information: purpose, warning about transport, response shape, latency, use-case fit, and relationship to siblings. It is front-loaded with the core action and well-organized with the emoji warning and bolded key terms. No wasted words.

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 a non-standard transport method and specific output limitations, the description covers everything an agent needs: how to call, what is returned, what is not returned, and what to do with the returned `id`. Output schema exists, but the description still adds necessary context about the query string and response brevity. It is complete for correct invocation.

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 baseline is 3. The description adds the important fact that parameters must go in the query string, not a JSON body, which is not in the schema. It also restates defaults and range limits but the query-string note is genuinely additional semantic value.

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 ('the open web'), and characterizes the result as a 'lean result list.' It distinguishes from siblings by noting it returns only title/link/snippet and contrasts with post_tavily_search for content, making its role clear.

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 explicitly states when to use it: 'suits an agent that only needs to know what exists.' It also names the alternative (post_tavily_search) for when content is needed, and instructs to keep the `id` for post_scholar_search_explain. This is explicit when/when-not guidance.

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