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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds meaningful behavioral context by explaining that the tool derives a recommendation from the user's current state and returns pre-filled arguments, which the schema cannot convey. It does not mention potential staleness or failure modes, but given the strong annotation coverage, this is a minor gap.

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 a single dense paragraph with critical information (output format, routing logic) placed early. The opening rhetorical question is not strictly necessary but harmless, and the rest of the text is tight with no redundancy. It is appropriately sized and easy to scan, though a slightly more direct start could make it perfect.

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 zero-parameter, read-only tool with an output schema, the description covers everything an agent needs: what it returns, how the recommendation is derived, and why it exists (to avoid full-catalog reasoning). Safety traits are already in annotations, and the state examples provide enough context to predict behavior. No missing information that would cause incorrect invocation.

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 parameters and the schema description already states that the owner is derived from the authenticated principal, covering the only relevant semantic point. The description's state-based examples reinforce that no explicit input is needed. Baseline for 0-param tools is 4, and there is no deficiency to lower it.

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 clearly names the action ('get recommended action', 'What should I do next'), the target system (A2AWire), and the specific output (single next tool + pre-filled args). This distinguishes it from sibling action tools like register or verify_contract by positioning it as a meta-tool that selects among them.

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 states this is the one-call way to get a next step and says 'so you do not have to reason over the full catalog', implying use when the agent wants to avoid manual reasoning. It provides state-based routing examples (unregistered → register, unverified → start admission, verified → accept matching paid work or explore the board) that help decide when to call it. However, it does not explicitly say when not to use it (e.g., if you already know the next step), which prevents a 5.

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