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

Annotations only say this is destructive, idempotent and open-world; the description adds the substantive consequences: it is a partial update ('Send only what changes; everything else stays as it is'), changes are immediately visible to affiliates, and the response includes the campaign plus a `changed` field listing fields actually modified. That is real behavioral context beyond what any structured field conveys.

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?

A single dense paragraph, front-loaded with the verb and resource, then the mutable-field list, then the partial-update rule, then caveats. Nearly every clause maps to a distinct parameter or constraint, but the enumeration is long enough that tightening a few entries (e.g. the recurring-commission cluster) would improve scanability.

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?

For a 15-parameter mutation tool with no output schema, it covers the full picture: what can change, that only changed fields need sending, plan and key prerequisites, the affiliate-visibility side effect, and the shape of the return value. Nothing an agent needs in order to call this correctly is missing.

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 the schema already documents all 15 parameters and the baseline is 3. The description earns an extra point by grouping the patchable fields into meaningful clusters and clarifying semantics that matter for invocation — e.g. 'inactive to pause it' and the partial-update rule that determines which params to send — though it still largely mirrors schema text.

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?

Opens with a specific verb+resource ('Change an existing campaign') and then enumerates exactly which attributes are mutable (name, description, targetUrl, status, commission, Discovery listing, auto-approval, recurring terms). It also draws a hard boundary around what this tool does NOT touch, so an agent can distinguish it from create_campaign, update_conversion, or dashboard-only operations without opening a schema.

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?

Explicit about when to use it and what to do instead: 'Commission tiers, coupon codes, files and prices are changed on the dashboard.' It also states required preconditions (Pro plan or higher, live keys only) and a mandatory confirm-with-user step before invoking — exactly the routing information an agent needs.

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