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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description discloses key behavioral traits: each result's context is 'verbatim page text' that 'usually already contains the answer', and that 'Extra topics dilute ranking.' These are non-obvious behavioral details that help the agent interpret results correctly, with 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 front-loaded with purpose and key behavior, then uses a well-organized bullet list for topics. Every sentence earns its place: the topic list is necessary, and the result format note is essential in the absence of an output schema. No fluff or redundancy.

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?

Given 3 parameters, no output schema, and moderate complexity, the description provides full context: it explains result fields (rank_order, url, title, context), the nature of context (verbatim chunks), and how to bridge to read_documentation. It covers all needed operational knowledge for an agent to select and invoke the tool correctly.

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?

Although the schema has 100% parameter descriptions, the description adds significant meaning by defining each topic category (e.g., 'troubleshooting -- errors, "how to fix" (NOT for conceptual/feature questions)') and explaining topic selection strategy. This provides semantic enrichment beyond the schema's terse 'topic name' descriptions.

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 begins with 'AWS docs search', clearly stating the tool's verb (search) and resource (AWS docs). It distinguishes itself from siblings by explicitly directing users to 'read_documentation' only when chunks lack detail, and references 'retrieve_skill' in the topic list. This is a specific, differentiated purpose.

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?

Provides explicit when-to-use guidance: 'Use read_documentation only when the chunks genuinely lack the needed detail,' and instructs 'Pick ONE topic. Add a 2nd ONLY if query genuinely spans domains.' It also clarifies that troubleshooting is NOT for conceptual/feature questions. This fully covers usage context and alternatives.

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