write_episode

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

No annotations are provided, so the description carries the full behavioral burden, and it largely does not. Beyond the hint that entities enable later lookup ('so it can be looked up later'), it says nothing about what writing actually does: whether duplicates are deduplicated, whether the episode is immediately retrievable/confirmed, what vault_name prerequisites exist, or how the confidence and temporal fields affect retrieval. For a mutation tool with zero annotation coverage this is a significant gap.

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?

Three sentences, front-loaded with the action and the primary use/avoid distinction before parameter guidance. Every sentence carries information; the only mild inefficiency is that the entities clause mixes a parameter hint into the usage sentence rather than structuring guidance separately.

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?

An output schema exists, so return values need not be explained, but the tool is a mutation with eight parameters, zero schema descriptions, and no annotations — and the description does not cover the temporal fields (valid_from, occurred_at) or confidence/source that materially change what gets recorded. An agent could invoke it, but with a poor picture of the resulting state.

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 for all eight parameters, and it only addresses three: content, entities ('give the entities it is about so it can be looked up later' — explains why, not format) and salience ('between 0 and 1 for how much it matters'). The remaining five — source, confidence, valid_from, occurred_at, vault_name — get no explanation of meaning, format, or effect, so the compensation is partial.

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 ('Record something that happened or something the user stated, in an episodic vault') and immediately draws the content-type boundary: 'facts with a lifetime — situations, preferences, relationships, plans — rather than for documents.' That contrast gives an agent a concrete test for separating write_episode from write_doc without opening either schema.

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?

Clear when-to-use criteria ('facts with a lifetime') and an explicit when-not ('rather than for documents'), which is the main sibling distinction. However, it never names the alternative tools, and it gives no guidance on write-vs-revise/supersede/invalidate decisions despite those siblings existing — an agent updating an existing fact gets no routing advice.

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