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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful context beyond annotations: determinism, evidence-bounding, signed delivery, and a 0.001 USDC cost. No contradiction with annotations exists.

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?

The description is short and front-loaded with the main purpose. The semicolon splice and trailing cost note are slightly awkward, but every phrase contributes meaningful information.

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 and annotations cover the safety profile, but the description never defines what a 'bounded inference microtask' is or what input shape is expected. Since the schema is an open object, this leaves the input contract underspecified.

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?

The tool has zero named parameters, so the baseline is 4. The open schema (minProperties 1, additionalProperties true) is not explained, and the description does not specify what fields a microtask should contain, but with no defined parameters the burden on the description is limited.

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 states a specific verb and resource ('complete a bounded inference microtask', 'return a directly usable answer') and adds distinctive traits like 'deterministic, evidence-bounded and signed'. It does not explicitly contrast with sibling phion_* tools, so it stops short of full differentiation.

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?

There is no guidance on when to use this tool versus alternatives such as phion_search, phion_enrich, or phion_execute. The phrase 'bounded inference microtask' implies a use case, but no explicit conditions, exclusions, or selection criteria are provided.

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