chat_knowledge

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

Despite annotations already declaring read-only, the description adds valuable operational context beyond them: it calls an LLM (implying cost/latency), has no other side effects, and lists specific quota limits per plan (Free 10, Starter 50, Pro 200, Enterprise 2000). This exceeds the annotation baseline.

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 three concise sentences, each with a distinct purpose: what it does, when to use it (and when not), and operational constraints (read-only, quota). No redundant or filler content.

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?

The description, combined with a fully documented schema and annotations, covers the tool's return type, use cases, alternatives, quota, and safety profile. Since there is no output schema, the explicit mention of 'synthesized natural-language answer with citations' sufficiently communicates the expected response.

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?

The input schema provides 100% coverage for both parameters (question with length constraints, model with enum options). The description adds no additional parameter semantics, which is the expected baseline when schema coverage is high.

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 uses a specific verb ('Returns'), identifies the resource ('AlgoVault knowledge bundle'), and specifies the output ('synthesized natural-language answer with citations'). It also explicitly distinguishes the tool from the sibling search_knowledge by contrasting LLM synthesis vs. raw ranked snippets.

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?

Clear usage guidance is provided: 'Use when you need an explanation, code pattern, or how-to', and an explicit alternative is named ('for raw ranked snippets without LLM synthesis use search_knowledge'), including the trade-off that it is faster and has no quota cost.

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