add_facts_batch

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

With no annotations provided, the description carries the full behavioral disclosure burden. It explicitly states that each fact is committed independently, which is critical for understanding partial-failure semantics, and describes the return summary (added count, duplicates count, errors). It does not cover permissions, rate limits, or duplicate detection criteria, but the core behavior is disclosed. The description adds meaningful context that is not present in the schema or annotations.

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 concise and well-structured. The opening sentence states the core purpose immediately, followed by an 'Args' section listing the fields in a clear bullet-like format, and a 'Returns' section describing the output. Every sentence earns its place; there is no fluff or repetition. The information is front-loaded and easy to scan, making it efficient for an agent to parse.

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 minimal schema and lack of an output schema, the description provides the necessary context: the fact field structure and the return summary. It covers the independent-commit behavior and the counts/errors in the response. It does not explicitly address error scenarios (e.g., what happens if a single fact fails) but the return summary implies partial success. The description is largely self-contained and sufficient for correct invocation, though it might benefit from clarifying how duplicates are identified and whether there is any limit on batch size.

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 input schema is minimal, only specifying 'facts' as an array of objects with additionalProperties true, giving 0% coverage. The description compensates by enumerating the expected fields (subject, predicate, object required; plus optional fields like subject_type, context, etc.) and clarifying that they match add_fact's structure. It provides meaning beyond the schema, though it does not explain each field's type or constraints, relying on a reference to add_fact. This is sufficient context for an agent to construct valid input.

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 purpose: 'Add multiple facts, committing each newly created fact independently.' It specifies the exact action (adding multiple facts), the resource (facts), and a key distinguishing behavior (independent commits). This separates it from the sibling add_fact, which handles a single fact. The verb and resource are precise, making the tool's role unambiguous.

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 implies this tool is for adding multiple facts at once, but it does not explicitly contrast with add_fact or state when to choose one over the other. There is no mention of 'use this when you need to add several facts in one call' or any alternative or exclusion criteria. The context is present but not made explicit, so an agent must infer the usage scenario. It is not misleading, but it could be stronger.

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