create_record

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

No annotations are present, so the description carries the full behavioral burden. It discloses the side effect (creating a record and audit event), the REVIEW_REQUIRED response, and the returned UUID, version, and trusted configured local actor. It stops short of fully clarifying whether REVIEW_REQUIRED means the record is persisted or only queued for review, which is a meaningful residual gap.

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 definition is compact and front-loaded: the most important warning about legacy behavior and the alternative comes first. Every sentence adds distinct value, and there is no filler 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?

Given the output schema exists, return-value explanation is less critical, and the description covers the key behavioral trap, the side effect, and the search-first precondition. It is less complete on parameter semantics and the precise meaning of REVIEW_REQUIRED, but it still gives an agent enough to decide whether to use the tool or route to the modern alternative.

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 parameter meaning relies entirely on the prose. The description gives only indirect hints that data is a generic JSON object and that title-like names are not unique; collection_id is never explained. This does not sufficiently compensate for the schema silence.

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 identifies a legacy direct-write operation that creates a generic JSON-object record and audit event. It distinguishes itself from the prepare_write/commit_write siblings by labeling itself as legacy and explicitly naming the modern alternative. The core purpose is unambiguous despite the REVIEW_REQUIRED behavior.

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 description tells agents to prefer prepare_write/commit_write instead, making the primary alternative explicit. It also instructs agents to search first because names are not unique, which is a concrete precondition for safe use. This provides both a when-not-to-use and a how-to-use-it-appropriately guideline.

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