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

The description adds value beyond annotations by detailing the exact error format ('returns {"error": ...}') and retry safety ('always safe to retry'). While annotations already state readOnly and idempotent hints, the description enriches with concrete error behavior and examples. No contradictions with annotations.

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 moderate length but front-loads the core purpose clearly. Each sentence adds unique value: purpose, typical example, usage guidance, sibling differentiation, error handling. Could slightly reduce redundancy (e.g., mentioning 'FREE' is already in the title), but overall efficient and well-structured.

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 simple single-parameter input, rich annotations (readOnly, idempotent), and included error handling details, the description fully covers what an agent needs. It explains input constraints, expected output format, error behavior, retry safety, and when to choose alternatives. The presence of an output schema reduces the need to describe return values.

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% with 1 parameter ('slug'), and the description provides a concrete example ('linkedin-outreach') and sources the parameter from an external tool ('exactly as returned by list_products'). This adds practical context beyond the schema description, such as validation and source of valid values.

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 the tool loads a 'free gateway skill' with its 'complete instructions' for a product. It specifies the exact verb ('Load') and resource ('free gateway skill'), and distinguishes it from siblings like 'get_full_skill' by noting differences in input and plan requirements.

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 when-to-use guidance: 'Use when the caller wants usable instructions immediately.' It also specifies when not to use it ('Not for the product's other skills') and names the alternative ('get_full_skill with a skill_name, which requires a paid plan'). Additionally, it covers error handling behavior for invalid inputs, making invocation clear.

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