get_scene

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

With zero annotations the description carries the full burden and does so richly: it discloses that licence differs by stage, that withheld stages produce absences not zeros, that a licence holder is named, that the caller must print scene_hash and the licence line in first/middle/last frames, and that earlier vintages return unknown_vintage. Named error states (licence_refused, unknown_vintage) and anti-loop guidance are exactly the beyond-schema context an agent needs.

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 opening is well front-loaded, but the body is a dense run-on paragraph that mixes parameter semantics, licence rules, and multi-frame rendering instructions. Every element is relevant, yet the lack of structure makes it hard to scan for the arguments an agent must actually pass.

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?

For a 4-param tool with an output schema, the description is thorough: it explains absences vs zeros, licence staging, error outcomes, and citation requirements. It even describes return contents (rows, table twin, alt text, receipt, canonical URL) that the output schema likely already covers, and only the 'country' parameter is left unexplained.

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 and it largely does: scene_id (only 'ireland-builds' exists, example given), purpose ('analytical' default or 'promotional' with refusal behavior), and vintage (ISO date, omitted = current, earlier = unknown_vintage). The 'country' parameter (default 'ireland') is never mentioned, which is the one gap preventing a 5.

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+resource: 'The data to DRAW one scene, nothing rendered', and clarifies scope with 'use it when asked for a chart, still or short clip of a figure you can cite.' It implicitly separates itself from data-query siblings (query_data, compare) by being a rendering-input tool, but never names an alternative 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?

Gives clear trigger conditions ('when asked for a chart, still or short clip of a figure you can cite') and states that nothing is rendered by the tool itself. It also covers purpose-based refusal (promotional + advertising-forbidden licence → licence_refused). No explicit sibling routing or when-not-to-use exclusion, keeping it below a 5.

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