affiliate_list_actions

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

The readOnlyHint annotation already signals safety, but the description adds meaningful behavioral detail beyond it: it explicitly states the tool never executes an action, drives a browser, or checks live auth, and that it returns an explicit unsupported-scope result for unknown network/brand. This goes beyond the annotation without contradicting it, though it doesn't discuss pagination or result-size limits.

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?

Three dense sentences deliver the core purpose, usage context, safety caveats, return type, and sibling alternatives. The structure front-loads the main function in the first sentence and progressively adds practical details, with no filler or repetition.

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 includes the return type (ActionMapEntry[]), lists the key fields returned, covers the unknown-network/brand edge case, and points to related tools. With no output schema, this is fairly complete, though a reader might still want a richer definition of ActionMapEntry and what 'local readiness' means.

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 0% schema description coverage, the description compensates by naming all four filter dimensions (network, brand, effect, channel) and clarifying their role as filters. It also ties the effect/channel enums to the action categories and mentions the unsupported-scope result for unknown network/brand. However, it doesn't elaborate on value formats or the meaning of an omitted filter, leaving some ambiguity.

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 the doing-surface actions...the configured adapters declare," and enumerates the output fields (channel, effect, default authority tier, local readiness). This clearly differentiates it from sibling network-specific tools like affiliate_list_networks and affiliate_run_diagnostic by naming exactly what it catalogs and what it does not do.

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 gives explicit when-to-use guidance: "Use this to see what is possible and what it would cost in approvals before granting a write credential or planning a change." It also provides concrete alternatives, directing users to affiliate_run_diagnostic for live credential/endpoint health and affiliate_list_networks for network discovery, and states what the tool does not do (never executes an action, drives a browser, or checks live auth).

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