recent

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

With no annotations, the description carries the full burden and does disclose real behavior: the 24h default window, the fact that all write kinds count, and crucially the empty-result semantics ('a zero here really means nothing was captured'). It stops short of ordering, result caps, or pagination, which matters for a list tool.

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 scope statement and the default window before the framing and the `since` format note. Slight redundancy between the 'every kind of write' list and the 'did what I just write land' restatement, but nothing is wasted.

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?

For a two-parameter read tool with no annotations and no output schema, the description covers purpose, timing default, and empty-result meaning well. It omits any explanation of the `initiative` filter and any hint of return shape or ordering, so an agent still has gaps before calling it confidently.

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 coverage is 50%: `since` is already documented in the schema with the same `30m`/`3h`/`2d` examples, so the description largely repeats it. `initiative` has no schema description and the description says nothing about it, leaving half the parameters unexplained.

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 (list) and resource (everything captured in the time window), then explicitly widens scope beyond the obvious sibling: 'every kind of write, not only episodes: references, claims, tasks and jots all count.' An agent can distinguish this from `episode` 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?

Frames the use case concretely — 'the verb that answers "did what I just write land?"' — which tells the agent when to reach for it. It implicitly contrasts with the `episode` sibling but never names a when-not case or an alternative such as `search`/`recall` for historical lookups.

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