Everything that just closed

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds real value beyond that: an auth prerequisite ('Needs a key'), the default time behavior, and the returned per-lane fields.

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?

Compact: one clause describing scope, a parenthetical for the time parameter, a short return-shape fragment, and a terse auth note. Front-loaded and free of filler, though the fragments are dense enough to require domain familiarity.

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 no output schema and 0% schema coverage, the description carries the full burden and covers the return field names, time format/default, and key requirement. It falls short on the `lanes` parameter's accepted format and on any indication of result volume or failure behavior.

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 0%, so the description must compensate. It does well for `at`, giving the exact format 'YYYY-MM-DD HH:MM' and the default ('the minute just closed'), but the `lanes` parameter is only obliquely referenced ('every lane that closed') and its syntax for selecting a subset is never explained.

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 concretely states what is returned: every series the key holds across all lanes that closed at a boundary, plus the per-lane shape (bar, complete, series, values). It is specific but uses domain jargon ('plan', 'lane', 'series') without definition and never names a sibling such as tilla_window or tilla_latest to differentiate scope.

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?

'In one call' hints this is the bulk/broad fetch versus narrower siblings, and the default 'minute just closed' implies the common call pattern. However, there is no explicit when-to-use, when-not-to-use, or named alternative, so routing between this and tilla_window/tilla_latest/tilla_sample is left to inference.

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