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

Annotations show readWrite, idempotent, non-destructive. Description adds key-value pair storage, scoping by identifier, persistence details (authenticated persistent, anonymous 24h), and pairing with recall/forget. No contradiction.

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?

Four focused sentences, front-loaded with core purpose. Each sentence adds distinct value: purpose, usage trigger, key-value mechanism, persistence and related tools. No redundancy or filler.

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?

Covers storage behavior, scoping, persistence, and integration with recall/forget. Missing output schema but description sufficiently explains tool's effect. Could mention overwrite behavior on same key, but not critical.

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% with clear descriptions. Description adds contextual examples for key (e.g., subject_property) and notes value accepts any text. Adds semantic clarity beyond 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 saves data for later reuse across conversations or sessions, with concrete examples like resolved tickers or user preferences. It distinguishes from sibling tools like recall and forget by mentioning them.

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 'use when you discover something worth carrying forward' and pairs with recall and forget for retrieval/deletion. Implicitly guides when not to use (if data is ephemeral or not needed later). Lacks explicit when-not or alternatives beyond the mentioned siblings.

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