remember

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

Discloses persistence ('durable', 'future session can recall it') and storage guidance (self-contained fact). Annotations only have readOnlyHint=false; description adds value by warning against storing obvious code details, but omits any side effects or access considerations.

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?

Concise paragraph of ~100 words with no wasted sentences. Purpose, usage, examples, and parameter notes are all front-loaded and efficiently presented.

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 key aspects: what to store, when, and how. Lacks details on retrieval (likely covered by sibling) and storage scope, but adequate for a simple memo tool without 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 has 100% coverage; description adds formatting guidance ('single self-contained fact') and example content. This helps the agent form correct parameter values beyond the schema's minimal descriptions.

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?

Clearly states the verb 'store' and resource 'durable decision or conclusion'. Examples and exclusions (no transcripts) distinguish it from siblings like 'recall' and 'blame'.

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?

Explicit when to use (right after decision settled, bug resolved, user says 'remember this') and when not to use (transcripts, routine conversation). Provides clear context without naming alternatives but effectively guides the agent.

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