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

With no annotations provided, the description carries the burden of behavioral disclosure. It adds a meaningful constraint: 'Never sends raw unredacted private transcripts,' which is a privacy/redaction behavior. However, it does not disclose other behavioral traits such as whether events are appended, whether there are limits, or what happens on invalid experience_id. The description adds some value but leaves significant behavioral 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 short and front-loaded with the core purpose. The privacy note is a useful second sentence. It is concise, though the section references (§24, §7) are cryptic and may not help an agent without access to those sections.

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 tool has 3 required parameters, no enums, 0% schema coverage, and no annotations. The description does not explain the event_type vocabulary, the expected shape of event_data, or the relationship to the experience lifecycle. An output schema exists, which helps, but the description alone is insufficient for an agent to call this tool correctly with well-formed arguments.

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 the three parameters. It mentions 'structured actions, observations, and state changes' which loosely maps to event_data, but it does not explain what event_type values are expected, what experience_id refers to, or the structure of event_data. The description adds minimal parameter-level meaning beyond the schema's bare property names.

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 ('Record') and resource ('observable event in an ongoing experience episode'), and references sections §24 and §7, which adds domain context. It distinguishes itself from siblings like cognitive.start_experience and cognitive.submit_outcome by focusing on recording events within an ongoing episode, though it doesn't explicitly name those siblings.

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 implies usage: it is for recording observable events, actions, observations, and state changes during an experience episode. It does not explicitly state when to use this tool versus alternatives like cognitive.submit_outcome or cognitive.report_transfer, nor does it provide exclusions or prerequisites. The guidance is implied rather than explicit.

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