memory_ingest

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

Annotations indicate readOnlyHint:false, consistent with a write operation. The description explains the deduplication behavior and mentions that query will surface saved items later. It does not contradict annotations. However, it could mention any side effects or limitations (e.g., storage limits), but it's sufficient for the annotations provided.

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 well-structured, starting with the core purpose and a bold directive, then expanding with examples and parameter advice. Each sentence contributes value. Minor reduction possible, but it's not overly verbose given the complexity.

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?

No output schema exists, but the description doesn't need to explain return values. It covers what to save, when, and how to tag/handle duplicates. It doesn't explain error states or confirmation messages, but for a memory ingestion tool, the description is sufficiently complete to guide an AI agent.

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 parameters are documented. The description adds value by advising to always pass meaningful title and tags, and explaining the deduplicate parameter's usage. This goes beyond the schema's basic descriptions. Other parameters are not elaborated, but the key ones are enhanced.

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: saving important context to persistent memory. It lists specific examples (project decisions, user preferences, etc.) and provides a heuristic for when to use it. It effectively distinguishes from sibling tools like memory_query (search) and memory_get_item (retrieve) by focusing on ingestion.

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?

Excellent guidelines: explicitly says to call whenever learning valuable information, gives concrete examples, and provides a heuristic ('if you would be sad to lose this fact'). It also advises on parameters (title, tags, deduplicate) and encourages over-saving. The guidance is actionable and clear.

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