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

Goes well beyond the annotations (which only declare non-read-only, open-world, non-idempotent, non-destructive) by disclosing the whole escalation ladder: SMS with a 10-minute single-use link, auth requirement (logged in or PIN), 2-minute fallback to a phone call, account-level gating rules (opt-in, quiet hours, per-day, budget, credit), billing via billed_eur, and the refusal shape {status: refused, why}. That is exactly the operational context an agent needs before triggering a paid, side-effecting notification.

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 the core action and escalation behavior, with the parameter notes compressed into the tail. Dense but nearly every clause carries new information; the return-shape enumeration is somewhat redundant given an output schema exists.

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 cross-channel, money-spending notification tool, the description covers trigger condition, delivery path, fallback timing, auth, gating rules, and failure modes. Since an output schema exists, the return-value enumeration is optional, and nothing an agent needs to invoke 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 description coverage is 100%, so the schema already documents reason, message, and session. The description's 'reason: done | blocked | decision' and 'message: max 120 characters' merely restate the enum and schema text, adding no syntax or format meaning beyond it. Baseline 3 is correct when the schema carries the parameter semantics.

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+resource (notify the human owner via SMS) and immediately scopes it to the case where they are not on the call page. It is clearly distinguishable from sibling call_me and from status/decide/next, so an agent can pick it 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?

Explicitly says 'Prefer this over call_me' and gives the selecting condition ('when they are not on the call page'), which implies call_me is the alternative when the human is present. It stops short of stating the when-not case outright, so it is strong routing guidance rather than a complete decision rule.

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