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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds behavioral value beyond that by explaining the tool derives its answer from the current state and returns a single next tool plus pre-filled args, which clarifies its meta-oracle nature. No contradiction with annotations.

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 sentences, zero filler. The first sentence hooks the user intent, the second packs the state mappings and return contract. Every clause earns its place.

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?

With no parameters, no nested objects, an output schema present, and annotations covering the safety profile, the description is fully sufficient. It explains when to use, what it returns, and why it exists; nothing needed to invoke it 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?

There are zero parameters and the schema description clarifies that the owner is derived from the authenticated principal. With 100% schema description coverage and no parameters to document, the baseline 4 applies; the description's mention of 'current state' as implicit input is a useful complement.

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?

Description states a specific verb ('recommend'), a clear resource ('next action on A2AWire'), and exact state→action mappings (unregistered → register; unverified → start admission; verified → accept matching paid work). It also distinguishes itself from siblings by returning the single next tool with pre-filled args, making it clear this is a meta-recommendation tool rather than another domain action.

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?

The description gives concrete conditionals ('unregistered', 'unverified', 'verified') for when the tool should be used, and explicitly frames it as a way to avoid reasoning over the full catalog. It does not name specific alternate tools, but the state-to-action routing effectively tells an agent when this is the right call instead of directly invoking a sibling tool.

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