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

With only readOnlyHint=false and openWorldHint=true available, the description adds substantial unstated behavior: it requires a connected Picorn account with credits, is billed at 1.2x the fal price, gives a concrete cost anchor (~1 ct for ~1 MP), and names the return payload (inline preview, public imageUrl, chargedCents). That is exactly the billable/external-dependency context annotations cannot express.

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?

One dense paragraph that is correctly front-loaded: purpose, then mode selection, then the library-first rule, then cost/return. It is efficient with no filler, though the run-on construction of the middle 'kind' clauses slightly slows parsing.

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?

No output schema exists, and the description compensates by naming the returned fields (preview, imageUrl, chargedCents). Auth and billing prerequisites are covered too. The remaining gap is that half the geometry/pagination-style parameters receive no behavioral explanation, which is a minor omission for a straightforward generation call.

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 33%, so the description must compensate. It does clarify 'kind' well (default photo maps to Krea 2 Turbo, text maps to GPT Image 2.5 Flare for lettering-heavy mockups) and implies prompt content and cost scaling with resolution, but width, height, aspectRatio and preview are left entirely to the schema — three of six parameters get no added meaning.

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 ('Generate a new picture on fal') and immediately distinguishes the two modes with the underlying models (Krea 2 Turbo vs. GPT Image 2.5 Flare). An agent can separate this from picorn_edit_image, picorn_design_image and picorn_generate_vector_assets without opening any schema.

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?

Explicitly prescribes 'Library first' with the alternative tool named (picorn_search_library, or search lines in picorn_blueprint_compile) and gives the when-not condition: generate only when no fitting hero photo exists and the design would benefit massively. This is a full routing rule, not an implied one.

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