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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description consistently adds scope detail: only loaded pages are searched, the live internet and post-load updates are excluded, and results come back as excerpts with URLs. This reinforces the closed-world read profile with useful context rather than contradicting it.

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?

Purpose is front-loaded and each subsequent sentence (scope limits, fallback behavior, failure protocol) carries operational value. It runs a bit long for a one-parameter search tool, but nothing is redundant 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?

Because an output schema exists, return-value details need not be restated, and the description is otherwise complete for a search tool: scope, behavior, and failure handling are all covered. The one missing piece is any distinction from the very similar sibling search_pages.

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% with a single query param, so the baseline is 3. The description goes further by advising how to formulate and reformulate the query (formal names for abbreviations, synonyms), which adds real meaning for how to set this parameter beyond the schema's single example.

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 (search within pages loaded from the site) and what it returns (excerpts with URLs), so the operation is unmistakable. The main gap is that it never differentiates itself from the sibling search_pages, which sounds nearly identical, leaving selection between the two to inference.

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 explicit context ('when asked about the site, use this first') plus a concrete fallback loop: vary wording, expand abbreviations, then read returned page candidates, and never guess if still unfound. It does not name any alternative tool (e.g. search_pages, site_overview), so when-not-to-use-this is left implicit.

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