Create memory note

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

The description discloses rich behavioral details beyond the annotations: it is confined to DATACRON_WRITE_PATHS, never overwrites existing files, writes a durable operation record, and relies on human-in-the-loop approval. These specifics add significant value beyond the raw readOnly=false annotation.

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 three sentences, each earning its place: proactive trigger, core action with rejected format, and safety behavior. No redundancy or filler words.

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 covers usage, safety, and the rejected format, but for a tool with 10 parameters and 0% schema coverage, it leaves many parameter semantics unexplained. The presence of an output schema reduces the need to describe returns, but the agent still needs to understand parameters like supersedes or expected_hash to use the tool fully. The description is good overall but incomplete for full self-sufficiency.

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 has 10 parameters with zero descriptions, and the tool description only explains the 'rejected' parameter format ('option -- reason'). Other important parameters like rel_path, supersedes, expected_hash, and last_verified are left entirely unexplained, leaving the agent to guess their meaning and usage.

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 action: 'Write a new typed _memory Markdown note.' This is a specific verb+resource that distinguishes it from read/search/patch tools. It also adds proactive context ('Call this proactively when a durable fact...'), making its purpose unambiguous.

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 explicitly says when to call ('when a durable fact, confirmed decision, or user preference emerges') and when not to ('Skip speculation and one-off chatter'). It does not explicitly name alternative tools, but the context imparts that this is for new notes rather than appending or patching, so it's clear but lacks direct alternatives.

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