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

Annotations already flag destructive=true and openWorld=true, but the description adds real behavioral detail beyond them: that it rejects other operation kinds before reserving or applying anything (atomicity/validation behavior) and that it changes external Meta state and may affect spend. Prerequisite auth/approval semantics are also surfaced, which the annotations do not express.

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 tight clauses, front-loaded with the precondition and action, followed by the input-binding rule and the side-effect warning. No redundant or filler text; every sentence carries weight.

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?

An output schema exists, so return values need not be described. For a destructive, open-world mutation the description covers action, precondition, input binding, and spend impact, which is most of what an agent needs; only the connection_context parameter and the consequence of a digest mismatch are unaddressed.

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 description coverage is 0%, so the description must carry the burden. It gives meaningful roles for two parameters ('stored plan selected by approval_ref and expected_plan_digest' - selector plus integrity digest), but adds nothing about connection_context, the mctx_v1_ format, or the digest's failure mode, leaving one of three parameters undocumented.

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?

States a specific verb and resource: 'pause the approved product family campaigns in Meta', which is concrete and actionable. It is not differentiated from the near-duplicate sibling products_delivery_pause_confirm (or precomputed products_delivery_pause_prepare), which an agent could easily confuse with this operations_confirm_* tool given the sibling naming overlap.

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?

Implies the precondition 'After explicit user approval' and establishes that the stored plan is the only input ('uses only the stored plan selected by approval_ref'). However, it never names the alternatives (products_delivery_pause_prepare, operations_deny_approval, or the other operations_confirm_* tools) or states a when-not condition, leaving routing between confirm/prepare/deny largely to inference.

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