get_context

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

Even though readOnlyHint and destructiveHint already communicate safety, the description adds valuable behavioral detail beyond annotations: it performs hybrid search, reranks, applies MMR, enforces a token budget, and structures output for direct LLM answering.

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 dense but efficient: the first sentence describes behavior and output, and the second provides actionable selection guidance. No filler is present.

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?

Combined with the output schema and read-only annotations, the description gives the agent enough understanding of the tool's purpose, behavior, and usage context. There is little risk of selecting the wrong retrieval 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 description coverage is 0%, so the description needed to compensate, but it only meaningfully explains the token budget and implicitly the query. Filters and collection are left to name inference, which is not enough for fully reliable invocations.

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 names a concrete operation (hybrid retrieval with reranking and MMR) and a clear deliverable (a formatted context block with numbered citations), making it easy to distinguish get_context from the raw search_* siblings.

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 explicitly says to prefer this tool over raw search_* tools when the goal is to answer a question rather than inspect search results, giving both a clear when and a clear when-not signal.

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