mdan_memory_remember

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal one important behavioral trait: 'Identical memories are reinforced, not duplicated', which informs idempotency and deduplication behavior. However, it does not disclose other potential side effects, such as whether existing memories are updated, how confidence affects reinforcement, or any failure modes (e.g., unknown agent). The description adds some value beyond the schema but leaves significant gaps.

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 two sentences long and every word contributes. It front-loads the core action and then adds a critical behavioral nuance. There is no fluff or redundancy, making it an exemplar of concise, structured documentation.

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?

Despite being a relatively simple tool with 5 parameters, the description omits essential context: it does not explain when to use this over sibling tools, it does not describe the meaning or constraints of 'tags' or 'content', and it does not clarify the effect of 'confidence' beyond the schema's terse hint. An agent would have to infer or experiment to understand the full contract, which is inadequate for a tool with multiple parameters and no output schema.

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?

The schema description coverage is only 40% (only 'agent' and 'confidence' have descriptions). The description compensates partially by listing the allowed memory types, which mirrors the enum for 'type', but it does not explain the meaning of each type, nor does it describe 'tags' or 'content'. Since the schema leaves these parameters underdocumented, the description should have provided more detail; it does not, leaving the agent to guess at the semantics of key parameters.

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 uses a specific verb ('Store') and a clear resource ('memory in an agent's persistent sidecar'), and enumerates the accepted memory types (observation, preference, project context, decision) which match the schema enum. This clearly distinguishes it from sibling tools like mdan_memory_recall, mdan_memory_forget, and mdan_memory_list, so an agent can immediately understand what this tool does.

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 provides no explicit guidance on when to use this tool versus alternatives. It does not mention that this is the write operation for persistent memories, nor does it contrast it with mdan_create_decision_record or other storage-like siblings. An agent must infer usage from the verb 'store' and the context of other memory tools, which is insufficient for clear decision-making.

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