lg_generate

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

With no annotations supplied, the description carries the full disclosure burden. It does well on process behavior (the agent, not the tool, authors the SVGs; validation via lg_validate is expected) and names the SVG constraints (viewBox, self-contained, text fallback, small-size legibility). But it says nothing about what the call actually returns (text brief? structured spec?), whether the spec is persisted, whether repeated calls are idempotent, or any cost/latency, which are the material traits for a 'generate a spec' tool with no output schema.

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 sentences, front-loaded with the deliverable, then the workflow, then provenance. Dense but every clause carries information; the parenthetical archetype list is the only mildly bulky element and it is load-bearing for the concepts parameter.

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 multi-step creative tool with six parameters, the description covers purpose, output composition, and the validation loop, which is enough for an agent to invoke it correctly. The remaining gap is the return shape and whether the brief is returned inline or written somewhere, which matters because no output schema exists.

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% and every parameter is already documented in the schema, so the baseline is 3. The description adds only one piece of semantic mapping — that the 'concepts' count becomes N distinct creative directions drawn from the named archetypes (geometric letterform / abstract symbol / mascot / negative space / wordmark) — but says nothing about how 'style', 'colors', or 'format' shape the brief beyond what the schema already states.

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 a complete logo design brief + SVG authoring spec for a project') and enumerates the deliverables: design summary, N creative directions, and strict SVG rules. It also makes clear what the tool is NOT (it does not emit the SVG itself; 'The AI (you) draws one SVG per direction'), which separates it from any sibling that generates assets directly.

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?

Gives an explicit follow-on workflow: draw one SVG per direction per the spec, validate each with lg_validate, then present the concepts. It does not, however, distinguish itself from the other generator siblings in the toolset (ia_generate, g_generate) or say when a logo brief is the wrong choice versus an icon/graphic one.

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