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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is partly covered. The description nonetheless adds real substance: budget enforcement, persistent idempotency, acceptance-criteria evaluation, a signed completion envelope, and the pricing note ('no gateway surcharge'). It stops short of describing failure/retry behavior or the dry-run semantics.

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?

Two tight sentences, front-loaded with the gateway purpose and flow, with a pricing clause that earns its place. Dense but not padded; density does cost some readability for a 7-parameter tool.

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 7-parameter, nested-object, no-output-schema mutation tool, the description leaves meaningful gaps: dry-run behavior, input shape, atomic budget units, acceptance-criteria pointer syntax, and what happens when criteria fail are all unaddressed. Both schema and description are thin on parameters.

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 carries the burden, and it only partially compensates. It conceptually covers budget (max_budget_atomic), idempotency (idempotency_key), acceptance criteria, and target_service, but says nothing about the 'atomic' unit format, the JSON-pointer syntax for acceptance criteria, the objective field, or what dry_run does.

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?

The description names a specific verb and resource ('execute one selected PHION service') and frames the tool as a 'Universal PHION execution gateway' that also budgets, idempotency-checks, evaluates acceptance criteria, and returns a signed envelope. That is far more informative than restating the name, but it never explicitly contrasts itself with siblings like phion_preflight or verify, so an agent must infer the boundary.

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?

'Execute one selected PHION service' implies this is the terminal step after discovery/selection, but no condition is given for choosing this over phion_preflight or verify, and no prerequisites or exclusions are stated. Usage is deducible from context rather than spelled out.

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