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

Resolves the apparent tension between a 'search' and readOnlyHint=false by explaining it creates a temporary saved search (an event set, cursor-paginated, kept ~24 h) without mutating doors/users/rights. That is real value beyond the annotations. It stops short of stating rate limits or whether concurrent searches accumulate, so not a full 5.

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?

Front-loads what it searches, then the side effect, then the default and the routing rule, with no filler sentences. The parenthetical asides and trailing 'POST /event_sets' add slight density, but every clause carries information an agent needs.

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?

Despite having no output schema, the description describes the return shape (event set id, cursor pagination, ~24 h retention) and the follow-up call, which is what an agent needs to chain correctly. The 8 parameters are fully documented in the schema.

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 already 100%, so the baseline is 3, but the description adds a default not present in the schema (past 90 days, the maximum width) and ties the interval semantics to the cursor continuation flow. It adds genuine meaning over the field-level descriptions without re-listing every filter.

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 ('Search the access log') and enumerates the event kinds covered (unlocks, denied attempts, lockdowns, admin changes), scoping it to the first page. This clearly separates it from kisi_get_event_set, which it names as the continuation tool.

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?

Explicitly states the default window (past 90 days, max width) and the exact condition for switching tools: 'If status is still in_progress or cursor is set, call kisi_get_event_set with the returned id.' It also pre-empts misuse by noting no door, user or access right is changed.

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