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

Goes well beyond the readOnly/idempotent annotations by disclosing the exact gate sequence (workspace capabilities, then per-call policy, then Number rules when from_number_id is set), the always-on high-risk-country hard block, and the negative guarantees: no reserve, charge, or review row is written. The explicit 'not checked' list (allowed_agents, concurrency, wallet reserve) is exactly the kind of scope boundary an agent needs to avoid over-trusting a positive result.

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 purpose and verdict in the first sentence, then layers gate order and exclusions, so the most decision-relevant content comes first. The middle sentences are dense and parenthetical-heavy, and the dangling 'stage outbound_number_rules' fragment reads awkwardly, but little of the content is genuinely redundant.

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 tool with no output schema, the description does well on the gate model and read-only guarantees, but it leaves the return shape underspecified beyond the three verdicts and the meaning of `stage` — no indication of what reason/detail fields accompany a block. The missing routing guidance relative to evaluate_outbound_policy is also a real gap given that sibling exists.

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 only 33% schema description coverage across 15 parameters, the description carries real weight: it explains that from_number_id triggers the Number's own rules stage and that channel selects the voice-vs-SMS gate path, plus what `stage` means in the result. It still says nothing about to, phone_number, categories, campaign_id, amount_minor, relationship, or user_requested, so several parameters remain undocumented in both places.

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 (preflight) and resource (call/SMS against pre-dial gates) and names the concrete decision space (allowed|blocked|needs_review), which distinguishes it from create_outbound_call by making clear it answers rather than performs. An agent can tell what it returns 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 frames this as a check to run 'before placing' the call and ties it to create_outbound_call's questions in order, which gives clear when-to-use context. It also scopes itself with 'Not a full admission' and lists what is not checked, but it never mentions the closely related siblings evaluate_outbound_policy or check_number_requirements, leaving the agent to guess which preflight tool to pick.

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