Batch-render many .riv files/formats in one call

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

With no annotations, the description fully carries the behavioral transparency burden, and it exceeds expectations. It discloses sequential reuse of a single Chromium page, explains that failures are isolated, and specifies the per-job report fields (success/error/outPath/durationMs). It also preempts the expectation of a watch mode.

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 a dense but well-organized paragraph that front-loads the core purpose, then adds necessary operational details. Every sentence contributes distinct information: execution model, target use case, defaults semantics, and error handling. No filler or redundancy with the schema.

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?

This is a complex tool with nested objects and multiple output formats, and the description covers the key contextual gaps not present in the schema: the sequential page reuse, lack of watch mode, fault isolation, and the shape of the returned report. Given the rich schema and no output schema, this is a complete operational picture.

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 100%, and the schema already documents parameter constraints and defaults. The description adds meaningful semantic value by explaining how the 'defaults' object merges with each job and how job-level fields override shared options. It also clarifies the behavior of the jobs array in terms of ordering and isolated failures.

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 opens with a specific action ('Render a list of jobs') and names the exact resources/formats (.riv files, png/gif/apng/webm/sprites), distinguishing this batch tool from single-render siblings like riv_render_gif and riv_render_video. It clearly defines the two job input modes (rivPath and glob).

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 provides strong contextual guidance: it is built for CI/scripts, should be called repeatedly from a pipeline, and no watch mode is available because MCP is request/response. It also explains defaults merging and job-level overrides. However, it does not explicitly name alternative single-render tools or state when to prefer batch over single rendering.

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