Create memory note

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

Adds substantial context beyond the annotations: confinement to DATACRON_WRITE_PATHS, the never-overwrite guarantee, the durable operation record, and reliance on MCP client approval for human-in-the-loop review. This gives an agent a full safety picture. The write claim is consistent with readOnlyHint=false and the non-destructive claim is consistent with destructiveHint=false.

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 tightly packed sentences, each earning its place: proactive trigger, what to skip, what to write plus rejected-format rule, and safety behavior. The most decision-relevant information is front-loaded before the safety details.

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 covers the call decision (when, what, safety) for an 11-parameter operation, and the output schema covers return values so those need not be described. Minor gaps remain: no differentiation from append_journal as an alternative, and the optional metadata parameters (supersedes, expected_hash, last_verified, request_id) are unexplained — a small but real completeness cost for a tool this complex.

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?

With 0% schema description coverage across 11 parameters, the description must compensate heavily. It does clarify one parameter concretely — 'rejected entries in option -- reason format' — and 'typed _memory Markdown note' hints at title/rel_path/body. However, the other required parameters (tags, origin, confidence) and optional metadata fields (supersedes, expected_hash, last_verified, request_id) receive no semantic explanation, leaving meaningful gaps.

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 verb and resource — 'Write a new typed _memory Markdown note' — and gives the exact trigger conditions (durable fact, confirmed decision, user preference). It differentiates from the patch/update siblings by emphasizing 'new' and 'never overwrites existing files,' and from append_journal by the memory-note vs journal distinction.

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?

Provides explicit when-to-use guidance ('Call this proactively when a durable fact, confirmed decision, or user preference emerges... do not wait to be asked') and clear exclusions ('Skip speculation and one-off chatter'). It stops short of naming sibling alternatives and stating when to choose them instead, so the alternative-routing dimension is not fully covered.

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