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

Annotations already declare readOnlyHint/destructiveHint=false, so safety is covered. The description adds non-obvious behavioral context: this endpoint 404s on the PCC gateway, runs as a separate service, and returns signing address plus chain ID. That is meaningful disclosure beyond the 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?

Four sentences, each contributing distinct information (not-gateway-served, separate service, do-not-use-for-settlement, return payload). It is front-loaded with the surprising constraint, though the negative framing could be tightened.

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?

No output schema exists, so the description correctly compensates by naming the return values (EIP-712 signing address, chain ID). For a zero-parameter read tool it covers the deployment caveat and the settlement anti-pattern. Marginally could have stated the positive use case, but it is complete enough to call correctly.

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 takes zero parameters, and the rule sets the baseline at 4 when there are no parameters to document. Nothing further is required or expected here.

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 concrete resource and return payload: the oracle's EIP-712 signing address and chain ID. It is specific enough to distinguish this from pcc_oracle_verify and pcc_verifier_health, though the heavy 'what it is not' framing slightly muddies the primary purpose.

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?

It gives explicit when-not-to-use guidance: agents never call the oracle to settle a job, and settlement belongs to the gateway after pcc_job_complete. It also warns the route only answers where a deployment fronts it (404 elsewhere). It stops short of stating the positive trigger condition for calling it, but the exclusion and alternative are clear.

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