Central Intelligence

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

With no annotations provided, the description carries full burden and excels: discloses write operation nature, encryption at rest, vector embedding generation, quota costs ('1 operation against the API key's monthly quota'), and return values ('memory ID and timestamp').

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?

Seven sentences cover persistence model, security, search indexing, usage conditions, exclusions, return values, costs, and workflow—zero waste. Front-loaded with core action ('Store...') and structured logically from 'what' to 'when' to 'costs'.

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?

Despite lacking annotations and output schema, description fully compensates by disclosing return structure, persistence guarantees, and side effects. Comprehensive for a 5-parameter tool with enum-based scoping and billing implications.

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%, establishing baseline 3. Description adds semantic categories for content ('fact, decision, or preference') and contextual examples ('architecture decisions, user preferences') that supplement the schema's technical constraints, justifying a score above baseline.

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?

Opens with specific verb+resource ('Store a fact, decision, or preference in persistent memory') and explicitly distinguishes from sibling tool 'recall' ('Use remember (not recall)'). Also differentiates from 'forget' by describing when to use each in the workflow.

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 positive conditions ('when you learn something worth keeping: architecture decisions...'), negative exclusions ('Do not use for ephemeral scratch data, secrets, or large files'), and names the alternative tool for deletion ('Use forget to delete outdated memories').

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