index_knowledge

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

With annotations readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description adds context by specifying the operation is 'local' and builds a BM25 index, suggesting side effects are confined to the local session. This clarifies that while it's a read operation, it sets up a searchable structure. It does not contradict any annotation and adds useful nuance about scope, though it could mention memory/performance implications.

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 a single, front-loaded sentence of 13 words, free of fluff. Every word earns its place, immediately conveying the action and outcome. It is perfectly sized for quick consumption.

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 tool has 6 parameters (moderate complexity) and an output schema exists. The description covers the overall purpose but omits any detail about parameters, return value structure, or edge cases like what happens with replace=true. Given the annotations already declare safety, this is adequate for a basic understanding but leaves gaps in knowing how to set up the index correctly, making it minimally complete.

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% and the description makes no mention of any parameters. All six parameters (limit, model, domain, fields, replace, instance) are left unexplained. Since the schema provides no defaults or descriptions, the description needed to compensate but entirely fails to clarify what these parameters do or how they interact. This leaves the agent guessing on parameter usage.

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 'fetch' and 'build' with concrete resources: 'a bounded slice of records' and 'a local BM25 knowledge index'. This clearly distinguishes it from sibling tools like search_knowledge and knowledge_stats, as it focuses on indexing rather than querying. It tells exactly what the tool does.

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?

There is no guidance on when to use this tool instead of alternatives. It does not mention exclusions, prerequisites, or compare to similar tools like search_knowledge or list_instances. The description only states the action without contextual 'when' or 'when not to use', so it fails to help an agent decide between this and related tools.

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