event_words_since

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

With readOnlyHint already declaring safety, the description still adds substantial behavioral context: the checkpoint/remaining pagination contract, the batch-boundary invariant ('a batch never ends between two Accounts with the same createdAt'), and the idempotency guarantee from complete field writes. This goes well beyond what the annotation provides.

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?

Purpose is front-loaded, followed by return shape and then operational guidance, and no sentence is filler — the return enumeration, boundary invariant, and idempotency note all earn their place. It is a dense unbroken paragraph rather than being over-long.

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?

There is no output schema, so the description carries the full return-shape burden and does so explicitly ({version, checkpoint, remaining, events} plus per-Event field list). Combined with pagination semantics, idempotency, and both parameters, an agent has everything needed to call and loop this tool correctly.

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%, so the baseline is 3, but the description adds real meaning: 'since' can be a previous checkpoint or an early time to read everything, and 'limit' interacts with the batch invariant rather than being a naive row cap. That is more than the schema's terse 'number of Events per batch.'

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+resource: retrieving the words recorded since a moment, framed for incremental folding into fields or cache refresh. It is clearly a delta/sync read, distinct in spirit from event_search and event_get_revisions. It does not, however, explicitly name an alternative sibling, 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 usage pattern: 'Pass checkpoint as the next since to continue; remaining counts the Accounts not yet returned,' which tells the agent how to drive the pagination loop. It also says reading the same words twice is harmless. It stops short of saying when to prefer this over event_search or context_pack.

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