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

Annotations already declare read-only/idempotent safety, but the description adds substantial behavior: a four-tier ranking order, non-semantic matching (one distinctive word beats a sentence), stemming/stopword handling, snippet windowing on the match, and pagination semantics (default 20, max 50, page while hasMore). This is context an agent cannot derive from the 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?

Front-loaded with the purpose and routing rule before ranking mechanics and pagination detail. It is dense and multi-clause, but nearly every sentence carries actionable information; only the ranking-tier enumeration is longer than strictly needed.

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?

No output schema exists, yet the description discloses the row shape (path, chars, match-windowed snippet) and the hasMore flag, so an agent knows both how to call it and what comes back. Complete for a 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 100%, so the baseline is 3, but the description adds genuine meaning: tagPath is framed as the narrowing lever for common terms (and sourced from get_categories), and page/pageSize defaults and the 50 cap are restated as operative constraints alongside the hasMore paging loop.

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?

Names a specific verb+resource ('keyword search across the Radix Wiki') and immediately scopes it ('the first call when you know what you are looking for but not where it lives'). This distinguishes it cleanly from list_pages, get_page and get_pages 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?

Explicit routing guidance: use this first when you lack a location, feed resulting paths to get_pages in one call rather than looping get_page, and narrow with tagPath when a term is common. It names both the trigger condition and the sibling tools to prefer instead.

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