render_mpr

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful behavioral context — it refuses failing series and its output is a PNG — but does not say whether the PNG is written to disk or returned inline, nor what the refusal response looks like.

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?

Two short sentences, front-loaded with the core action and followed by the one non-obvious failure condition. Nothing extraneous.

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 8 parameters fully documented in schema, readOnly annotations, and no output schema, the description covers purpose, output type, and a key failure mode. Only the return/handling behavior of the PNG is left underspecified.

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%, so every parameter including plane, window presets, and max_size is already documented. The description only echoes the plane concept and adds no format or default semantics beyond the schema; baseline 3 applies.

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 and resource: reconstructs axial/coronal/sagittal views from a slice stack and renders a PNG. That distinguishes it from render_image (single-image rendering) implicitly, though the sibling is never named, so differentiation requires inference.

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?

Adds a real precondition by pointing at check_geometry (refuses series that fail it), which tells the agent when this tool will error. However there is no explicit routing guidance such as 'use render_image for a single slice' or requirements for calling check_geometry first.

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