Add knowledge records

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

Annotations already mark this as a non-read-only but non-destructive, idempotent write. The description adds genuine behavior beyond that: validation is all-or-nothing (nothing is written if any record is invalid) and every problem is reported back. It does not cover permissions or how partial conflicts interact with the batch, keeping it short of a 5.

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 tight sentences, each doing a distinct job: what to store, how validation behaves, how duplicates are handled. Front-loaded with purpose and free of filler, though the parenthetical example list runs slightly long.

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?

With full schema coverage, an output schema and annotations in place, the description only needs to carry the write semantics, which it does well (atomic validation, dedup/upsert behavior). The gap is the relationship to edit_records and what a failed validation response looks like, which are minor given the output schema.

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 coverage is 100%, so entity, source, records, on_conflict and create_missing_refs are all documented in the schema itself. The description reinforces the conflict/dedup semantics of on_conflict and key matching but adds no syntax or value-level meaning beyond the schema. Baseline 3 applies.

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 opens with a specific verb and resource: store facts extracted from user-shared artifacts (receipts, statements, notes, logs). That is far more concrete than the tool name alone. It does not name a sibling alternative such as edit_records, so an agent must infer the boundary between adding and editing.

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?

It implies the triggering context (after extracting facts from something the user shared) and clarifies that repeated calls are safe because matches update or are skipped. However it gives no explicit when-not guidance and never points to edit_records as the alternative for correcting existing rows.

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