memory_ingest

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

Beyond the annotations (readOnlyHint false, destructiveHint false, idempotentHint false), the description discloses durable persistence, the default deduplicate behavior and how to override it, the default-space fallback, and the discoverability benefit of meaningful title/tags. It also conveys the intended proactive bias ('Better to over-save than to under-save').

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 long but every sentence earns its place, and the key directives are front-loaded and bolded ('Save important context', 'ROUTE BY TOPIC'). It is slightly dense, but for a high-stakes mutation tool with nine parameters and nuanced routing/dedupe behavior, the length is justified.

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 fully equips an agent to call this tool correctly: when to invoke it, how to choose titles/tags, how to handle duplicates, how to route to the right space, and what to do if spaces are unknown. The only minor gap is the space_id vs space name inconsistency, but the description explicitly says to reuse memory_list_spaces output, which mitigates the risk.

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 already 100%, so a baseline of 3 applies; the description adds extra semantic value by explaining that title/tags drive discoverability, that deduplicate:false forces a duplicate copy, and that space routing avoids the catch-all default. However, the description references `space:"<name>"` while the schema property is `space_id` (a UUID), which could confuse an agent if it follows the description literally instead of the schema.

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 opens with a specific verb and resource: 'Save important context to persistent memory.' It goes far beyond a generic restatement and clearly frames this as the tool for storing durable, cross-conversation facts, distinguishing it from querying (memory_query), batch ingestion (memory_ingest_batch), and other memory operations.

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 gives explicit when-to-use guidance ('Call this WHENEVER...'), concrete examples (project decisions, user preferences, debugging insights), a memorable heuristic, and even routing advice to memory_list_spaces. It also tells the agent when not to take the default path, warning against saving without a space in multi-space projects.

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