memory

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

With no annotations provided, the description fully discloses behavior: it explains that 'purge' is irreversible and requires confirm=true, 'promote' increases retrieval strength, 'demote' decreases it without deletion, and 'edit' preserves FSRS state. This is comprehensive and transparent.

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 a single dense sentence with a list of actions. While efficient and front-loaded, it could be slightly more structured (e.g., using a bulleted list) for easier scanning. However, it earns its place with every word.

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 (8 actions, 6 parameters, no output schema), the description covers all necessary information: each action's effect, parameter requirements (e.g., confirm for purge), and the result of operations (e.g., tombstone after purge). It is complete.

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%, but the description adds significant context beyond the schema, e.g., explaining that 'purge' permanently removes content/embeddings, 'promote' is a thumbs up, and 'edit' preserves FSRS state. This adds meaning that aids correct parameter usage.

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 'Unified memory management tool' clearly states the tool's purpose. It lists all possible actions (get, purge, delete, state, promote, demote, edit), each with a specific role, effectively distinguishing this tool from siblings like search, memory_graph, etc.

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 managing memory nodes but does not explicitly state when to use this tool over alternatives. For instance, it doesn't differentiate when to use 'memory' vs 'search' for retrieving memories. However, the action list provides implicit context.

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