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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description adds genuinely useful context beyond that: results are historical collected evidence rather than a live feed, on-sale aggregates keep nested evidence, and top-level theatre/format displays can be null when firstBookableEvidence is unknown.

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 with the core purpose front-loaded and no filler. The middle sentence about nested evidence and nullable fields is somewhat compressed and leans toward describing return shape that the output schema already covers, but it is not wasteful enough to penalize heavily.

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 an output schema present, the description need not explain return values, yet it spends a sentence on them anyway while omitting higher-value information such as pagination behavior and geospatial filtering semantics. The freshness caveat and nullability note make it adequate, but not complete for an 11-parameter filtered-list tool.

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 description coverage is 0% across 11 parameters, so the description must carry the load and it largely does not. It clarifies only that 'since' is an absolute ISO time; it says nothing about the zip/radius coupling, page/pageSize paging, dateFrom/dateTo windowing relative to 'since', or how movie/format/theatre narrow results.

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 and resource: find newly observed premium showings or new on-sale evidence since an absolute ISO time, and enumerates the returned fields. This clearly distinguishes it from search_showtimes and get_best_showings, which retrieve current showtimes rather than deltas, even though those siblings are not named explicitly.

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?

Usage is implied by the delta framing ('since an absolute ISO time') and the caveat that this is collected evidence rather than a real-time feed, which hints at when results may be incomplete. However, there is no explicit guidance on choosing this over search_showtimes, how to combine zip and radius, or whether to fall back to another tool when the evidence is sparse.

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