render_settings

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the write-capable but non-destructive profile is already known. The description adds genuine value beyond that by disclosing the mixed read-then-update contract and that only supplied settings are changed. It omits the read payload shape, whether null clears a value, and any permission or state preconditions.

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 compact sentence with no filler, front-loading the read behavior before the write behavior. It is dense enough that the read/write duality takes a second pass to parse, but no words are wasted.

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 six optional parameters, no output schema, and a tool whose primary mode is reading, the description should state what a read returns (current renderer, dimensions, limits) since structured fields cannot. It also leaves the semantics of passing null versus omitting a field unexplained, which matters for a partial-update tool with all-nullable parameters.

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 50%: quality, max_time and properties are documented, while width, height and max_samples are bare. The description partially compensates by mapping 'size' to width/height and 'limits' to time and sample caps, but it also names 'renderer', which is not a parameter, and never explains units, defaults, or what the generic properties bag accepts.

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?

Names a specific resource (render settings) and two operations: reading renderer, size and limits, and changing supplied values. An agent can tell this is a combined get/set settings tool, distinct from the render/render_animation siblings that actually produce output. It stops short of explicitly distinguishing itself from anything else, but the scope is 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 phrase 'changes the ones given' implies the default read behavior when no arguments are supplied and partial updates when arguments are, which is real implicit guidance. There is no explicit when-to-use, no prerequisites, and no statement about what happens if conflicting values are supplied or whether omitted fields are left untouched versus reset.

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