generate_model

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

With no annotations, the description carries the full burden; it discloses the returns (cga_source for later round-trips, model stats, local glb path, signed download URL, sha256, usage, warnings) which is useful. However, it does not disclose cost/quota behavior (the `usage` field hints at it), whether local files are written to output_dir, or timeout semantics.

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?

The structure is clean: a one-line summary, an enumerated mode list with a concrete example, and a Returns block. Every sentence carries information, though the 'Args: same as parse_cga' line is a shortcut that weakens the definition rather than adding value.

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?

The Returns section covers the absence of an output schema well, and the two primary modes are fully described. However, for a 9-parameter generation tool with 0% schema coverage, the majority of parameters go unexplained, leaving an agent to guess at behavior like download_glb and output_dir.

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?

With 9 parameters at 0% schema description coverage, the description only explains how `text`, `base_cga`, and `instruction` are used. seed, timeout_s, attributes, output_dir, download_glb, and initial_shape are left entirely to the schema titles, and the cross-reference 'other params same as parse_cga' pushes the burden onto another tool's documentation.

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?

The description states a specific action (generate a 3D model), names the underlying pipeline (NL2CGA + engine parsing), and explains the two generation modes (text vs. base_cga + instruction). It doesn't clearly distinguish the tool from generate_cga or generate_model's role relative to parse_cga, leaving sibling differentiation weak.

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 definition gives explicit mode-selection conditions: use `text` for a fresh description, or `base_cga` + `instruction` to revise an existing CGA. It doesn't say when to prefer generate_cga or parse_cga instead, so there is no exclusion guidance.

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