New project

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses that the project is palette-indexed (an important constraint) but says nothing about what happens on id/name collision, whether the new project becomes the active/selected one, whether anything is written to disk, or what a failed creation looks like — all critical for a mutation tool.

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?

Three short sentences, purpose front-loaded, then the ordering rule, then actionable sizing guidance. Nothing is redundant with the title and no sentence is filler.

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 9-parameter creation tool with no annotations and no output schema, the description covers intent and sizing but leaves the post-call state undefined (created project id? auto-selected? error behavior). It is adequate to call the tool, but not to predict its outcome.

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 100%, so the baseline is 3; the description earns above that by giving concrete size heuristics (16x16 icons, 32x32 characters, 64x64 bosses) that the schema does not encode. It also groups the parameters conceptually (canvas size, palette, frames, layers), though it does not touch id, tags, or durationMs.

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 ('Create an indexed pixel-art project') and enumerates the configuration surface: canvas size, palette, frames, layers. 'Always call this first' plus the 'new project' framing cleanly separates it from creation-adjacent siblings like sprite_load_project and sprite_save_project.

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?

'Always call this first' is an explicit ordering directive that tells the agent this is the workflow entry point, and the classic-size examples guide parameter choice. It stops short of naming when not to use it (e.g. when a project is already selected) or pointing at sprite_quickstart as a lighter alternative.

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