agent_remember

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

Discloses mutation, idempotency, and return value format. With no annotations, the description covers key behavioral traits, though it could mention failure modes or rate limits. Still, it is above average.

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 efficient sentences: first states purpose and persistence, second gives usage guidance, third covers behavior and idempotency. No wasted words.

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 simple tool with 2 fully-described parameters and no output schema, the description covers purpose, usage, behavior, parameter conventions, and return value. Sufficient for effective invocation.

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?

Adds meaning beyond schema: suggests naming convention for keys (lowercase dotted namespaces) and advises JSON-stringifying structured values. This is valuable guidance for correct usage.

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 states a specific verb (persist) and resource (non-secret key/value note in encrypted, on-disk agent memory). It also distinguishes from siblings by explicitly warning against using for secrets (use set_secret) and transient state (use chat scratchpad).

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?

Provides explicit when-to-use examples (recording stable agent context) and when-not-to-use (secrets, transient state) with named alternatives (set_secret, chat scratchpad).

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