Replace file text in a knowledge base and reindex it. On failure, inspect stage/file_id before retrying to ensure consistency.
Replace shared file text and reindex this base. Other bases sharing this file may change.
Writes are not atomic. Inspect stage/file_id on failure before retrying.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| file_id | Yes | ||
| knowledge_id | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (destructiveHint=true, idempotentHint=false), the description adds crucial behavioral context: writes are not atomic, other bases may change, reindexing occurs, and failed calls should prompt inspection of stage/file_id before retrying. This is exactly the kind of non-obvious behavior an agent needs.
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 short sentences, each earning its place: the core action, the side effect, and the retry/failure caveat. Critical information is front-loaded and there is no filler.
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 covers the most important operational risks for a destructive, non-idempotent mutation with no output schema: side effects, non-atomicity, and retry guidance. It falls slightly short on explaining the knowledge_id parameter and what exactly 'stage' refers to in the failure inspection step.
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 must compensate, but it only implicitly ties 'text' to file text and mentions file_id in the failure guidance. The knowledge_id parameter is left entirely unexplained, and no parameter-level semantics are 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 states a specific action: replace shared file text and reindex the base. It also discloses an important scoping fact ('Other bases sharing this file may change'), which clearly separates this update tool from sibling create/add/delete/search tools.
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 intended use is implied by the purpose statement, and the warning about other bases sharing the file suggests caution, but the description does not explicitly state when to choose this tool over alternatives or when not to use it. No sibling tool is named as a fallback.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.