record_batch

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

No annotations mean the description carries the transparency burden. It adds useful constraints like 'use ABSOLUTE dates' and the efficiency benefit, but does not describe return behavior, error handling, or durability. It's adequate but not rich.

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 dense and efficient, front-loading the usage preference with '⚡ PREFERRED' and then detailing item types. It could benefit from line breaks, but every sentence contributes value.

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 provides complete item type specs and usage rules (e.g., one per turn, absolute dates). Since an output schema exists, return values don't need explanation. It's fully sufficient for a batch write tool.

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?

With 0% schema coverage, the description fully compensates by specifying the items parameter: a list of dicts, each with a type (fact, fact_tree, lesson, goal, plan, activity, milestone) and their individual fields. This goes far beyond the sparse schema.

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 'stores N atomic items in ONE call', identifying it as a batch recording operation. It differentiates from sibling record_* tools by labeling it 'PREFERRED' for messages with multiple memories.

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?

Explicitly says 'PREFERRED for any message with multiple memories' and 'ONE record_batch per turn', providing clear when-to-use guidance. It also contrasts with separate record_* calls, making the alternative usage clear.

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