TD Build GLSL (live)

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

Since no annotations are provided, the description carries the full burden. It discloses key behavioral traits: for unsupported techniques, it does not fabricate connections and returns code with explanation; for supported techniques, it creates specific operators and lays them out. It also mentions the default parent COMP. However, it does not discuss permissions, overwriting behavior, or potential side effects.

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 description is a single well-structured paragraph that uses capitalization for emphasis (COMPILE, SUPPORTED, UNSUPPORTED) and logically separates the two cases. Every sentence contributes valuable information without redundancy. It is appropriately concise for the complexity of the task.

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?

Given the tool has no output schema, the description should at least hint at return values. It describes the side effects (creating operators) but does not specify what the function returns (e.g., success message, operator references). It also omits error handling or prerequisites beyond the bridge. For a complex build tool, this is a notable gap.

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 baseline is 3. The description adds some meaning beyond the schema: it provides examples for 'technique' (raymarching_basic, Gray-Scott Reaction-Diffusion) and clarifies the 'parent' default (/td_mcp/sandbox). However, this added value is modest relative to the schema descriptions.

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 uses a specific verb 'COMPILE' and clearly identifies the resource as 'GLSL shader technique' from the experimental GLSL knowledge base. It distinguishes between supported and unsupported techniques, and mentions the 'list' option for enumeration, which differentiates it from sibling tools like td_build_pattern or td_build_template.

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 description provides explicit guidance on when to use this tool: it handles supported techniques by creating operators, and unsupported techniques by returning code without connections. It mentions building into the sandbox by default and the requirement for the bridge (td_status). However, it does not explicitly state when not to use this tool or compare it to alternatives like td_build_pattern.

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