upsert_knowledge

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

No annotations are provided, so the description carries the burden. It discloses several behavioral traits: it compares MD5 hashes, detects additions/modifications/deletions, and is faster for small changes. It does not mention side effects like permanent removal from index, but the mention of deletions covers that. It could be more explicit about index mutation behavior, but overall it provides substantial transparency.

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 sentences, each earning its place: the first defines the core action, the second explains the mechanism, and the third gives performance guidance. No fluff or repetition.

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?

With zero parameters and an output schema present, the description provides sufficient context: what it does, how it works, and when to use it. It clearly differentiates from the full-index sibling, and the output format is handled by the 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?

The tool has zero parameters, so the baseline is 4 per the rubric. The description does not need to explain parameters, and the schema is empty. No additional semantics are required or provided.

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 clearly states the tool's function: 'Incrementally update the vector index' with a specific mechanism (MD5 hashes) and scope (only changed files). It distinguishes itself from sibling index_knowledge by emphasizing incremental updates.

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?

It explicitly provides usage guidance: 'Much faster than index_knowledge() when only a few files changed' implies using this tool for small changes and index_knowledge for full re-indexing. This addresses when to use the tool versus alternatives.

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