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

Annotations already cover readOnly/idempotent/closed-world, so the bar is lower, and the description adds value annotations can't carry: results are sections (not full pages), relevance-ranked, and each names its page and section. It still says nothing about the default limit, ranking quality, or what an empty result looks like.

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?

Two sentences, front-loaded with the core purpose; the query examples and the pointer to get_page each earn their place by disambiguating input style and next step. No padding.

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?

With no output schema, the description correctly steps in to describe the result shape (page + section per hit). It leaves the limit/pagination behavior unexplained, which is the only real gap for a two-parameter search tool.

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 0%, so the description must compensate. The worked examples ('sortable table', 'dark mode', 'error message on a field') do teach the query parameter that it accepts short keyword phrases or error text, but the limit parameter (default 8, max 20) is completely undocumented in either place.

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?

States a specific verb and resource — it finds reference sections that answer a question — and explicitly contrasts with the get_* siblings by framing itself as the search entry point whose results feed into get_page. An agent can tell it apart from get_page/list_* without opening any schema.

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?

Gives clear context for when to reach for it (a question or a few keywords) and names the downstream tool to call with the results. It stops short of naming an alternative or a when-not-to-use condition, so it is clear context rather than full routing guidance.

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