affiliate_skimlinks_list_programmes

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

With no annotations, the description carries the behavioral disclosure burden. It discloses the output ('Returns an array of Programme records') and the scope (joined or available), which is useful. However, it omits details about pagination, filtering, authentication, or any side effects (though listing is inherently read-only). It adds some context beyond the name but lacks rich behavioral detail.

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 two sentences, front-loaded with the action and directly followed by usage guidance and return type. Every sentence contributes: the first defines the scope, the second provides triggers and related tools. No filler or redundancy.

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 description gives a clear purpose and return type, but with 6 undocumented parameters and no output schema, an agent lacks crucial details needed to invoke it correctly (e.g., how status/categories filtering works, pagination semantics, or what fields a Programme record contains). It also omits authentication requirements and edge cases like empty results or the 'available to join' distinction. For a tool with this complexity, the description is incomplete.

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?

The input schema has 6 parameters (limit, cursor, offset, search, status, categories) with 0% description coverage, and the description does not explain any of them. Parameter names are self-explanatory, but the description adds no semantic meaning, leaving the agent to infer usage from names alone. With no schema descriptions and no additional context, this is a significant gap.

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 opens with a specific verb and resource: 'List affiliate programmes the publisher has joined on Skimlinks (or which are available to join).' It provides concrete example queries ('which merchants am I working with?', 'what programmes do I have on Skimlinks?') and distinguishes from siblings by naming Skimlinks and noting the return type (Programme records). It also explicitly pairs with get_programme and list_transactions, clearly separating it from other list_programmes tools for different networks.

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 explicitly states when to use the tool: 'Use this when the user asks...' with specific natural-language triggers. It also mentions complementary tools (get_programme for drill-down, list_transactions for activity), providing context. However, it does not explicitly state when not to use it or present direct alternatives for the same network, so it falls short of a 5.

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