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

The description adds significant behavioral detail beyond annotations: it states the tool never raises a protocol error but returns an error object, describes the error format with examples, and confirms every call is read-only and idempotent. This complements the readOnlyHint, idempotentHint, and destructiveHint annotations perfectly without contradiction.

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 well-structured with clear sections: purpose, example input/output, usage guidance, error behavior, and safety guarantees. Every sentence serves a purpose, and critical information is front-loaded ('Load a product's free gateway skill with its complete instructions'). While verbose, it remains efficient for the information density.

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 one parameter, an output schema, and annotations, the description covers all necessary context: purpose, input format, output structure, error handling, sibling differentiation, and retry safety. It even references list_products as a prerequisite. No gaps remain.

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 100% schema description coverage, the description still adds value by clarifying that the slug must be exactly as returned by list_products and providing an example ('smb-ops-desk'). This gives the agent a concrete reference for constructing valid input beyond the schema's constraints.

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 it loads a product's free gateway skill with complete instructions, and explicitly distinguishes it from get_full_skill which handles other skills and requires a paid plan. It also provides a typical input and output example, making the purpose unambiguous.

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 explicitly tells when to use this tool ('when the caller wants usable instructions immediately') and when not to ('Not for the product's other skills: those are named and need get_full_skill with a skill_name, which requires a paid plan'). It also explains error handling and retry safety, leaving no ambiguity.

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