render.save

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

Annotations already declare idempotentHint and destructiveHint, and the description reinforces the destructive nature with 'overwrite'. It adds genuinely new behavioral details: engine ('Eevee Next'), exact-camera guarantee, output formats (PNG or EXR), absolute path requirement, and the parent-directory prerequisite. No contradiction with annotations exists.

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?

A single dense sentence conveys the tool's purpose, scope, constraints, and output side effects without any filler. Each clause adds distinct information: the camera selection, bounded settings, write mode, path form, formats, and prerequisite. This is efficient and front-loaded.

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?

The output schema mitigates return-value concerns, but the input side is incomplete. With 9 parameters and no schema descriptions, a render/save tool that is destructive and guarded by expected_* fields needs more explanation for idempotency_key, expected_camera_identity, and expected_scene_generation. The description covers the general output behavior but not the safety/versioning semantics required to use the tool correctly.

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. It clarifies the meaning of path (absolute, parent exists, PNG/EXR), camera_name (exact camera), and the bounded settings (width/height/samples). However, it does not explain the required parameters expected_camera_identity, expected_scene_generation, or idempotency_key, leaving a meaningful gap.

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 is specific and action-oriented: 'Render one exact Camera' names the verb and resource, and the rest clarifies the output behavior ('overwrite an absolute PNG or EXR output path'). This implicitly distinguishes it from siblings like render.preview and viewport.capture, which target previews or viewports rather than a file write, though it never references an alternative by name.

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 gives clear usage context: it renders a specific camera, uses bounded Eevee Next settings, and requires an absolute path whose parent already exists. This effectively tells the agent when the tool is appropriate and what must hold before calling it. It does not explicitly discuss exclusions or alternatives, hence not a 5.

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