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 internal process (captures server-readable HTML/CSS, extracts Reference DNA, names what to borrow/avoid, gives a similarity-risk guardrail) and sets an expectation of originality. It also hints at a constraint with 'server-readable.' It does not discuss failure modes or side effects, but for a generation tool this is adequate.

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 moderately sized with a clear structure: hook, input instructions, process, and when-to-use. Every sentence adds information, though it is somewhat dense. It earns a 4 for being efficient without being overlong.

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 8 parameters and no output schema, the description provides a clear picture of the workflow and what the returned direction includes (borrow/avoid/guardrail). It does not detail the exact response structure, but response_format is in the schema. The tool's purpose, usage, and output components are covered well.

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 meaning beyond the schema by explaining favorite_bits as 'inspiration tokens, not copied components' and emphasizing that business is 'what YOU are building (not the reference).' This extra interpretation is valuable for the agent.

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 clearly states that the tool builds a reference-backed original build direction from a site without cloning it, and outlines the process (captures HTML/CSS signals, extracts DNA, names borrow/avoid, gives similarity-risk guardrail). This is a specific verb+resource+outcome that distinguishes it from sibling tools like get_reference or synthesize_direction_from_references.

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?

It provides an explicit use case: 'This is the right tool when the user says I like this site but don't want to steal it.' It also clarifies required inputs (reference_url, business) and optional favorite_bits. However, it does not explicitly list when not to use or name alternative tools, so it lacks exclusions.

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