revise

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

The description goes well beyond the annotation by explaining the mutation model: content addressing creates a new kb-id, the old record is retired but not deleted, search visibility changes, direct read by kb-id still works, and history can walk between versions. It also clarifies partial updates (omitted fields keep values).

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?

Every sentence in the description earns its place: when to use it, the core mechanic, the old-record behavior, and the partial-update rule. It is dense without being verbose.

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 definition gives the agent what it needs to call rev like safely: it explains what happens to the old and new versions, how search/read treat the revision, and how optional fields behave. With no output schema, the remaining detail burden is minimal.

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?

Only 2 of 7 parameters are described in the schema (kbid and content). The description adds the important partial-update behavior: omitted fields keep their existing values. But the meanings of tags, docid, title, description, and sectionType are still inferred solely from names, so the low schema coverage is not fully compensated.

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 is explicit and specific: it says when a stored fact is wrong, fix it with revise rather than adding a duplication. It also distinguishes the action from copy-like alternatives and from hard deletion, making it clear this is a correction/update operation.

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?

Opens with a clear condition, 'when a stored fact is wrong', and tells the agent not to create a second copy. It does not explicitly name sibling tools or state when to use unlearn/learn instead, but the usage context is strong.

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