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

Beyond the annotations (openWorldHint, idempotentHint, non-destructive), it discloses exactly what the probe does (anonymous GET, or MCP initialize/initialized/tools-list only), what it will never send (credentials, query params), and a critical economic rule: a declared budget is research input, not permission to charge. That is substantive behavioral context an agent cannot get from the structured fields.

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 purpose and the key constraint (free, save the token) are front-loaded, and nearly every sentence encodes a rule rather than filler. A few fragments ('save its private receipt token', the protocol list) read as clipped shorthand, but the density is justified for a tool with this many guardrails.

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?

Behavioral and follow-up guidance is thorough and the output schema covers return values, and the openWorld/idempotent annotations align with a non-destructive external probe. However, for a 10-parameter tool with zero schema descriptions, the undefined inputs (agent_reference, needed_result, idempotency_key) leave the definition incomplete for correct 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?

Schema description coverage is 0% across 10 params, so the description must carry the burden, and it only partially does: it clarifies allow_probe as permission confirmation, budget_cents as non-authorizing, protocol as anonymous GET vs MCP handshake, and target_url as a public target. It says nothing about task vs blocker vs needed_result distinctions, agent_name, agent_reference, or idempotency_key format/semantics, leaving over half the inputs undocumented anywhere.

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 makes clear this is a free public integration/diagnostic preview of a supplied target that returns a private receipt token, which distinguishes it from the paid path via place_order. The core verb is implied rather than stated cleanly ("preview", "probe"), so an agent must infer that it actually performs an anonymous GET or MCP handshake against target_url, but the resource and scope are unambiguous.

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 preconditions (a real blocked task, confirmed permission to probe), explicit exclusions (no credentials, query parameters, private targets, or application tool execution), and an explicit alternative for the paid outcome (place_order with diagnostic_id and token). The note that a healthy or inconclusive probe yields no paid report further routes the agent's next step.

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