Resume a session

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

With no annotations, the description carries the full burden and does a good job: it discloses that the call has a side effect (consuming the delta / advancing the watermark), that the result is deterministic ('the same watermark always yields the same answer'), and how to avoid the side effect. It does not describe error behavior, auth requirements, or the return envelope, so it is not exhaustive.

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 dense sentences, front-loaded with the return contents before the usage and parameter guidance. Every clause carries information; the determinism clause is the most expendable but still supports why the watermark contract matters.

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?

With one optional parameter and no output schema, the description does the extra work of sketching the return contents ('notes edited, facts asserted, knowledge updates (slot: old → new)'). It omits error/failure behavior and whether the watermark is ever reset, which keeps it from being fully complete.

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 100% and the schema already documents `since` as an ISO watermark that does not advance the boundary, so the baseline is 3. The description earns above baseline by explaining the consequence the schema omits: omitting `since` consumes the delta and advances the watermark, while passing it is a pure read.

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 uses a specific verb-plus-resource framing ('what changed since this tool was last called: notes edited, facts asserted, and knowledge updates') that tells an agent exactly what comes back. It implicitly separates itself from pure-read siblings ('pass an explicit `since` for a pure read'), but never names a sibling tool, so it falls short of full differentiation.

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?

It gives a concrete trigger ('call once at session start to continue where the previous session left off') and distinguishes the two modes of use, consuming vs pure read. No sibling alternatives are named, so it is a strong context statement rather than a full routing guide.

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