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

With no annotations, the description must carry behavioral disclosure. It does disclose a constraint (paid work refused) and redirects payments to an HTTP endpoint. However, it omits critical traits: what the tool does, side effects, required permissions, and return behavior.

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 sentence, but it is not front-loaded with purpose. It spends its brevity on a payment constraint rather than the tool's core action. The structure is misleading: the main clause describes what the tool is not, not what it is.

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 tool with one undocumented parameter, no output schema, and no annotations, the description is severely incomplete. It fails to explain the tool's action, the parameter's meaning, or when to use it versus siblings. An agent would have to guess to invoke it 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?

Schema coverage for the single 'url' parameter is 0%—no description in the schema—and the tool description says nothing about what 'url' represents or how to format it. The agent is left guessing whether it's a witness URL, a callback URL, or something else.

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 only restates the tool name ('Witness check') and adds a payment constraint. It never states what the tool actually does—no specific verb, resource, or outcome. An agent cannot tell whether this tool verifies witnesses, checks witness availability, or something else.

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 implies a negative usage condition ('paid work is refused over MCP') but gives no positive guidance on when to call witness_check vs siblings like budgets or verify_receipt. The alternative surface (POST /check) is mentioned, but not framed as a tool alternative for specific tasks.

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