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

Annotations declare readOnlyHint=false and openWorldHint=true; the description reconciles the surprising non-read-only hint by stating 'Uses one read and saves the result in the user's Puley history', so an agent understands the side effect is a history write, not a destructive mutation. It also discloses the upstream data source. What it does not cover — rate limits, whether history writes are user-visible or removable — is minor given destructiveHint=false.

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?

The core content (what it returns, in both modes) is front-loaded in the first sentence, with parameter hints trailing. It is dense and runs long as a single sentence, but no clause is filler — the Fandango attribution, the two return shapes, and the history-write note each carry information.

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, the description still specifies return shape for both modes — per-film rating, runtime and nearby theater count, or per-theater showtimes grouped by format (IMAX, Dolby, 3D) with ticket links. Combined with the parameter formats and the history-write disclosure, nothing an agent needs to invoke it correctly is missing.

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%, so the description carries the full burden, and it does: place gets accepted formats ('a ZIP (90036) or "Austin, TX"'), date gets an example and a default ('e.g. 2026-11-07 (default today)'), and movie is defined implicitly by the 'for one movie' mode. All three parameters are given meaning the schema does not supply.

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 names a specific verb+resource ('What's playing at the cinemas nearest a US ZIP code or town, and when, from Fandango') and spells out two distinct modes: a film list for a place, or every nearby theater's showtimes for one movie. It also names the source (Fandango), which separates it from streaming siblings like where_to_watch and from ticket_prices.

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 clear from the mode description — omit movie to get a film list, pass a movie to get per-theater showtimes with ticket links — and the 'for one movie ... with links to buy tickets' clause implicitly routes price/buying intent here rather than to ticket_prices. There is no explicit when-not guidance or named alternative, so it stops short of a 5.

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