celiums-memory

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: persistence ('survives across all sessions and machines'), automatic classification ('classified by type and importance'), and additional processing ('emotional analysis, assigns importance score, updates circadian interaction tracking'). This covers critical aspects like data longevity and internal handling, though it could mention potential limitations like storage constraints or error conditions.

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?

The description is appropriately sized and front-loaded, starting with the core purpose and key features. Every sentence adds value, such as explaining memory types, usage scenarios, and behavioral details. However, it could be slightly more streamlined by avoiding minor redundancy (e.g., 'information' repeated in context of 'content').

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 the tool's complexity (persistent storage with classification and analysis) and no annotations or output schema, the description is largely complete. It covers purpose, usage, behavioral traits, and parameter context. However, it lacks details on return values or error handling, which would be beneficial for a tool with no output schema, leaving some gaps in full operational understanding.

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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema, such as implying the purpose of 'content' ('information to remember') and 'projectId' scoping, but does not provide significant additional semantics. Baseline 3 is appropriate as the schema does the heavy lifting, and the description does not compensate with extra insights.

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's purpose with specific verbs ('store information in persistent memory') and resources ('memories'), distinguishing it from sibling tools like 'recall' (which likely retrieves) and 'absorb' (which might process). It explicitly mentions what types of information can be saved (facts, preferences, decisions, context), making it distinct and actionable.

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?

The description provides explicit guidance on when to use this tool ('to save facts, preferences, decisions, context, or any information that should be recalled later') and when to use alternatives (implied by distinguishing from siblings like 'recall'). It also specifies scoping rules ('scoped to current project by default — use projectId="global" for cross-project memories'), offering clear context for application.

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