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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lowered, and the description still adds real behavior: it 'preserves UNKNOWN and abstains when evidence is insufficient' and never authorizes payment or execution. What it does not disclose is what an abstention or UNKNOWN actually returns, which matters for an openWorld resolver.

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?

Three short sentences, no filler, and the core purpose is front-loaded before the behavioral caveats. The dense jargon ('provider-neutral capability resolution') costs a little readability but nothing is padded.

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 resolver with a nested constraint object, mutually-exclusive input shapes and a 3-value mode enum, the description covers the conceptual contract but not the invocation surface. With no output schema present, the description should also indicate what a resolution result looks like, and it does not.

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% across 4 parameters, including an 11-field nested constraints object and an executionMode enum with SHADOW/ADVISORY/PREFLIGHT values. The description says nothing about task vs capability, the anyOf requirement, what constraints are honored, or what the three modes mean, so it does not compensate for the coverage gap at all.

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 gives a specific verb+resource ('capability resolution') and frames scope with 'provider-neutral' and 'free'. It implicitly separates itself from phion_execute by stating it is 'advisory only: never authorizes payment or execution', but it never names or contrasts with the closer siblings phion_discover, phion_search_services or phion_preflight, leaving the boundary fuzzy.

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?

Usage is only implied: the 'advisory only' clause signals this is the non-committing step and that phion_execute is the committing one. There is no explicit when-to-use statement, no prerequisites (e.g. when to prefer preflight over resolve), and no exclusion rules, so the agent must infer the decision boundary.

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