save_memory

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

With no annotations, the description carries the full disclosure burden and does substantial work: it reveals that content is embedded locally and indexed for semantic search (a side effect worth knowing), that <private>…</private> blocks are stripped before storage, and that secret-like content is rejected. It stops short of stating what happens on duplicate content, whether the call is idempotent, or what is returned.

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?

Four short sentences, front-loaded with purpose, then usage, then behavioral caveats. Nothing is repeated and every sentence contributes new information the agent could not get from the schema or annotations.

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?

For a five-parameter write tool with no annotations and no output schema, the description covers purpose, intended content, storage side effects, and input sanitization rules. The main omission is the return value (e.g., whether a memory ID is returned for later update/delete), which matters given the sibling mutation tools.

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%, so all five parameters (including tags, metadata, importance, and the memory_type enum) are already documented in the schema, including the decay semantics of importance. The description adds no parameter-level detail beyond echoing the content categories, so the baseline 3 applies.

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?

States a specific verb and resource: "Save information to long-term memory," and elaborates the kind of content it holds (facts, decisions, preferences). It is clear what the tool does, but it never distinguishes itself from the sibling update_memory, so an agent cannot tell from the description whether to save new content or update an existing memory.

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?

"Use this to store facts, decisions, preferences, or any context worth remembering across sessions" gives a concrete usage context and implicitly scopes it to durable rather than transient content. There are no named alternatives or exclusions, so the boundary with update_memory, delete_memory, and the ephemeral memory_type remains for the agent to infer.

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