remember_fragment

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

No annotations provided, so the description carries full burden. It details dedup mechanism (SimHash), entropy scoring, automatic merging with salience boosting, and pinning behavior. This provides good behavioral insight, though it omits auth or performance details.

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 concise with a brief intro followed by parameter explanations. Every sentence provides value, though some technical jargon (SimHash, Shannon entropy) could be simplified. Overall well-structured.

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?

The description covers the tool's core behavior, dedup, merging, and pinning. With an output schema present, return values need not be explained. It is largely complete, though it could mention that stored fragments are retrievable later.

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 0%, yet the description fully explains all four parameters with meaningful context, especially is_pinned (detailed budget reserve logic). It adds value beyond the schema's type and defaults.

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 it stores a context fragment with specific features: dedup via SimHash and entropy scoring. This distinguishes it from sibling tools like vault_write_action or recall_relevant by highlighting its unique processing.

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 implies usage for storing context fragments like code or tool output, but lacks explicit guidance on when to use this tool over alternatives. No exclusions or when-not-to-use scenarios are mentioned.

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