g_generate

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

With no annotations, the description carries the full behavioral burden and discloses the non-obvious contract: the tool does not draw anything, the agent draws the SVG itself from the spec, and validation is a required downstream step. That is the single most important behavioral fact about this tool. It stops short of covering failure modes, whether spec generation consumes quota, or any auth requirements.

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, each doing distinct work: what you get, when to use it, and the mandatory next step. The critical instruction (validate before use) is placed last but flagged with "ALWAYS" so it is not skimmable-past, and the "(you)" aside removes ambiguity about who draws the SVG.

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 three-parameter tool with a fully described schema but no output schema, the workflow (spec -> draw -> validate) is complete and self-sufficient. The residual gap is that the return value is never characterized, so the agent cannot anticipate the spec's structure or size before calling, though it will be self-explanatory once returned.

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 size, style, and description are already fully documented in the schema, including defaults and the note that g_validate injects width/height. The description adds no syntax, format, or guidance for the description parameter beyond what the schema states, so 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: it returns a generation spec for a custom SVG icon rather than the icon itself, and explicitly positions itself against i_search_all and g_validate. The one gap is that "a precise spec" is never concretized (format, contents), so the agent knows the role but not exactly what it will receive.

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 triggering condition ("Use when i_search_all finds nothing suitable") and an explicit mandatory follow-up step ("ALWAYS pass the SVG through g_validate"). An agent knows both when to select this tool and what to do immediately after, with no inference required.

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