knowledge_reindex

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

No annotations are provided, so the description carries the full load, and it delivers real operational traits: searches are blocked during the run, and re-running resumes after an interruption. It omits auth/permission requirements and expected runtime or cost, which would fully round out the behavioral picture.

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?

Three tight sentences, front-loaded with the action and scoped by configuration. Each sentence adds distinct value: purpose, when-to-use/alternative, and operational side effects.

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 one-optional-parameter migration tool with no output schema, the description covers the trigger, the migration semantics, the blocking of searches, and resumability. Nothing an agent needs in order to invoke it correctly is missing.

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 100%, so the single batch_size parameter is already fully documented ('lower uses less memory, higher is faster'). The description adds no parameter-level detail, so the baseline 3 applies.

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?

States a specific verb ('Re-embed') and resource ('every stored vector'), with the scope bound to the configured EMBEDDING_PROVIDER/MODEL. This clearly distinguishes it from the ingest siblings (knowledge_ingest_text/file/dir), which add content rather than migrate existing vectors.

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?

Explicitly states the trigger condition ('after changing the embedding model or dimension') and names the alternative it replaces ('migrate the existing store in place instead of wiping and re-ingesting'). The agent knows both when to use it and what the competing strategy would be.

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