search_aws_knowledge

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

With no annotations present, the description fully carries the behavioral burden. It discloses that sources are queried in parallel, that a slow or broken source degrades to an entry in errors rather than failing the call, and that snippets are intentionally shorter. It also sets expectations by directing the agent to read_aws_content for full content. This is strong behavioral context beyond what any schema could imply.

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?

Despite being longer than average, every sentence earns its place. The scope statement is front-loaded, then the when-to-use and when-not-to-use are clearly separated, and the parallel-query behavior and handoff to read_aws_content are provided without fluff. There is no redundant restatement of the input schema or output format.

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 search tool with three parameters, one required, an output schema, and two sibling tools, the description covers everything needed to invoke it correctly: the exact sources, the scoping boundary, the failure behavior, and the follow-up step. The only thing not described in detail is return formatting, which the output schema already documents, so the description is sufficiently complete without pretending to replace structured schema.

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 meaningful extra semantics. It explains what each source ('repost', 'kiro', 'builder') means, makes clear that 'plain keywords' are intended, and ties sources to the use-case list. It doesn't merely repeat the schema descriptions; it gives conceptual grounding and selection guidance.

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 opens with a crisp scoping statement: 'Search AWS knowledge sources that the official AWS Knowledge MCP Server does not cover.' It names the specific sources (repost, kiro, builder) and explicitly differentiates from the sibling tool read_aws_content by saying to pass promising URLs to that tool. An agent can immediately grasp what this tool searches and what it does not.

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?

The description provides explicit when-to-use and when-not-to-use guidance, including examples: troubleshooting threads for the same error (repost), questions about Kiro itself (kiro), and recent community write-ups (builder). It explicitly says NOT to use this tool for official AWS documentation, API references, blogs, What's New, Well-Architected guidance, or re:Post Knowledge Center articles because the official AWS Knowledge MCP Server indexes those and is better. This is exactly the kind of selective routing guidance an agent needs.

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