mnemos

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

While annotations cover readOnly/destructive/idempotent flags, the description adds no context about what 'destructiveHint=true' means for a creation operation, what happens if the relation already exists, or how openWorldHint affects the operation. Agent must rely solely on technical annotations.

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?

Extremely efficient at 6 words with front-loaded verb. However, the brevity crosses into under-specification given the complex behavioral hints (destructive, non-idempotent) that warrant explanation.

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?

Adequate for basic invocation given complete schema coverage, but lacks explanation of return values (no output schema exists), validation behavior, or the semantic implications of relation types like 'supersedes' or 'contradicts'.

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%, documenting all parameters including relation_type values and strength range. The description provides only generic context ('two memories') matching source_id/target_id, adding no syntax, format constraints, or semantic guidance beyond the schema 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?

Clearly specifies the verb (Create) and resource (relation between two memories), distinguishing it from sibling tools like mnemos_store (which creates memories) or mnemos_update (which modifies them). However, it lacks scope details like directional nature (source→target) or whether duplicates are allowed.

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 no explicit guidance on when to use this versus alternatives, no prerequisites (e.g., that source and target memories must exist), and no warnings about the idempotentHint=false behavior (calling twice likely creates duplicate relations).

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