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

With no annotations, the description carries the full behavioral burden: it does disclose the batching trait (multiple items in one call) and that entries are durable/persisted, which are traits beyond the schema. It says nothing about whether capture is additive versus merging, idempotency and duplicate handling, required permissions, or partial-failure behavior when only some arrays are supplied — the main things an agent needs before firing a mutation.

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?

Two sentences, roughly forty words, with the core action front-loaded and usage guidance immediately after. Every clause does work — 'ONE call' sets the batching contract, 'don't wait to be asked' sets the trigger, 'signal, not chatter' sets the quality filter. No redundancy or filler.

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?

Output schema exists, so return values need not be explained, and the schema covers parameters fully; the description fills the remaining gaps by defining payload categories and proactive timing. The residual weakness is that a multi-item write tool with zero annotations leaves merge/dedup semantics and workspace scoping implicit.

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 the schema already documents all four parameters, and the description intentionally mirrors them in plain language ('ground truths', 'lessons/decisions', 'quests'). The workspace parameter is never mentioned, and no format or syntax hints are added beyond the schema, so 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 with scope: batch-save durable knowledge in ONE call, and enumerates the three payload groups (truths, lessons/decisions, quests) that match the schema's arrays. The word 'batch' and 'ONE call' loosely imply contrast with single-item siblings like wyrm_quest_add, wyrm_truth_set, and wyrm_remember, but none is named, so differentiation is left to inference.

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?

Gives clear triggering context: use it as decision-grade facts emerge and don't wait to be asked, plus a filter rule ('capture signal, not chatter'). It never names the granular alternatives (wyrm_remember, wyrm_quest_add, wyrm_truth_set) or says when to prefer those over batching, so the routing burden stays on the agent.

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