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

Annotations only declare the generic profile (not read-only, idempotent, non-destructive); the description supplies the real behavior: off by default, the unconfirmed call returns pricing/implications/a question and changes nothing, and consent must come from the owner. This is exactly the state-transition detail annotations cannot convey.

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?

Front-loads what the tool does and the default state, then gives the consent flow and the sibling exclusion in short declarative sentences. No filler, and each sentence carries a rule an agent must obey.

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?

With no output schema and a fully documented input schema, the remaining burden is the approval workflow and the non-mutating dry-run behavior, both of which are stated. An agent has everything needed to call it without violating owner consent.

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 baseline is 3; the description adds meaning on top by explaining confirm_credit_spend as gating the returned disclosure and matters only after explicit approval, and by contrasting enable vs. disable semantics. Minor gap: the required analytics 'context' parameter is not mentioned in the description.

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 pair (enable/disable), the exact resource (automatic paid customer handoffs for a project), and the actor restriction (owner-only). It also names the sibling it does not cover ('Does not draft historical runs; use request_framework_handoff separately'), so it is distinguishable without opening the 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?

Gives explicit when-to-use rules per mode: enabling requires the confirm_credit_spend flow and explicit owner approval, disabling needs no spend confirmation, and historical runs route to request_framework_handoff. It also states an anti-pattern ('never infer consent from test execution or reading a draft').

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