save_memory

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does indicate that the operation creates a new node, computes a dense vector embedding, and performs conflict detection. However, it does not explain what conflict detection actually does—whether it blocks the save, returns a warning, or triggers deduplication—and it omits any side-effect or authorization details.

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 entire description is one front-loaded sentence with no filler. It leads with the action and object, then lists relevant attributes efficiently. Every phrase adds either operational clarity or meaningful behavioral detail.

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 presence of an output schema reduces the need to explain return values. However, for a tool with no annotations and several sibling tools, the description leaves gaps: conflict detection behavior is unexplained, the agent parameter is ignored, and there is no guidance distinguishing direct saving from extract_and_save_memory. The core create operation is clear, but the surrounding context is incomplete.

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 0%, so the description must compensate. It names category, importance, and project namespace, which maps to three of the five parameters, and 'dense vector embedding' hints at how content is processed. However, it says nothing about the agent parameter and does not clarify what content should actually contain, leaving the required parameter semantically under-described.

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 states a specific action ('Save') on a specific resource ('a new memory node'), clearly distinguishing this from sibling operations like edit_memory, delete_memory, or save_graph_relation. The added details about category, importance, project namespace, and conflict detection make the tool's purpose unmistakable.

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: call this when creating and persisting a new memory node. However, it provides no explicit guidance about when to prefer this over alternatives like extract_and_save_memory, edit_memory, or deduplicate_memories, and there are no exclusion criteria or prerequisites stated.

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