agent_memory

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

Annotations indicate non-read-only and non-destructive. The description confirms mutability through 'record' and 'approve' but adds ADR-style context. However, it omits details like concurrency or persistence guarantees, which would elevate transparency.

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?

Two sentences cover the entire functionality: one for overall purpose and one for action breakdown. No fluff, every part earns its place, and it is front-loaded with the core verb-resource pair.

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 complexity (9 parameters, 6 actions) and no output schema, the description lacks details on return values or error handling. While adequate for basic usage, it could be more complete for advanced scenarios like search result format or proposal lifecycle.

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%, so the baseline is 3. The description adds value by explaining the semantic intent of actions (e.g., 'record saves an ADR-style DECISION with its rationale') and linking parameters like 'rationale' and 'text' to specific use cases, surpassing the schema alone.

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 'Persist and recall project memory' and enumerates specific actions (record, search, list, propose, approve, reject), distinguishing this tool from siblings focused on other domains like execution or exploration.

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 explains when to use each action (e.g., record for decisions with rationale, propose/approve/reject for task proposals). While it does not explicitly state when not to use, the sibling context provides natural separation, and the guidance is clear enough for typical use.

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