list_scenes

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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently states that the tool reads configuration files, returns a JSON string, and describes the metadata content (slide counts, resolution, media files). It also explains the default directory resolution for 'workspace_dir'. This is adequate for a read-only discovery tool, though it does not cover edge cases like missing folders or empty scenes.

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 description is well-structured with clear sections (intro, file source, args, returns). Every sentence adds value: it names the exact file format, the producing command, default behavior, and return type. No filler or redundancy exists.

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 simple read-only tool with two optional parameters and a clear return type, the description is complete enough. It explains the input files, the arguments, and the output. It could mention error behavior (e.g., missing folder) but that is a minor gap given the tool's simplicity and the presence of a return 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 description coverage is 0%, so the description must compensate, and it does. The 'Args' section provides natural language semantics for both parameters: 'folder' specifies the directory with rendered assets, and 'workspace_dir' explains the environment variable fallback. This adds meaningful meaning beyond the schema's type/default information, though it could still elaborate on path normalization or validation.

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 clearly states the tool 'Discovers rendered scenes and their slide metadata' with a specific verb and resource. It further distinguishes itself from siblings by explaining it reads '<scene>.json' files produced by 'manim-slides render', making its role as an inspection/discovery tool unambiguous.

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?

The description explicitly says the tool reads files produced by 'manim-slides render', providing clear context for when it should be used (after rendering). It does not explicitly name alternatives or exclusions, but the context is strong enough that an agent can infer it complements preview/export/compile tools.

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