probe402

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the probing schedule, a published rubric, retained captures for traceability, and critically that blocked/rate-limited responses are distinguished from unreachable ones so a defended endpoint is never reported as dead. That last point materially changes how an agent should interpret a result. It omits freshness/latency of the 'current' reading and any rate-limit or auth considerations, keeping it at 4.

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 first sentence is brand framing ('The Machine Commerce Observatory...') and the last ('The same record our published reports are written from') is marketing that adds no invocation value, delaying the actual 'what you get' statement to mid-description. The middle sentences do earn their place, but front-loading is weak.

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 output schema, the description appropriately states what comes back (current reading + 7 days of counts) and how to read it, and the annotations cover the safety profile for this read-only tool. It is slightly thin on how an unknown/never-probed endpoint is reported, but is otherwise 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?

Schema coverage is 100% and both parameters are already documented with useful detail (the ep_+16hex id format, host-URL route listing). The description only restates 'by endpoint_id or by url' and adds no syntax, format, or precedence guidance (e.g. what happens if both are supplied). Baseline 3 for a fully-covered two-param schema.

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?

Names a specific verb+resource: independent readings of x402 and MPP endpoints, with the scope pinned down ('current observation plus 7 days of counts, by endpoint_id or by url'). The contrast with the sibling is only implicit ('7 days of counts' vs. the history tool's presumably longer window) — it never names probe402_endpoint_history, so a 5 is not warranted.

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?

Gives concrete triggers: 'Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo.' That is a real when-to-use statement. It stops short of an explicit when-not or a named alternative (e.g. 'for deeper history use probe402_endpoint_history'), so it does not reach 5.

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

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

Annotations only cover read-only and closed-world, so the description carries the rest and does well: it discloses independent probing on a published schedule under a published rubric, retained captures for traceability, and the important nuance that blocked/rate-limited states are distinguished from unreachable so a defended endpoint isn't reported dead. It omits anything about the response shape or pagination, keeping it out of 5 territory.

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?

It is a single dense paragraph that spends a full clause on branding ('The Machine Commerce Observatory') before the actionable content, and the em-dash-heavy construction slows scanning. Most sentences do carry information, so it is not padding, but the core purpose is not front-loaded.

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 output schema, the description should explain what a 'reading' contains, but it only gestures at 'quoting what, and how fast'. The 30-day window and per-call price live in the annotation title rather than the description. For a simple one-parameter tool this is adequate, not complete.

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 is a single parameter and schema description coverage is 100% (the schema explains the ep_ + 16 hex id format and points to the /coverage list). The description adds no parameter detail, which matches the baseline of 3 when the schema already does the heavy lifting.

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 conveys that the tool returns observations about x402/MPP endpoints (liveness, quotes, latency), but it never plainly states that this tool returns the *history* of those readings, nor does it distinguish this from the sibling probe402_endpoint_grade. 'The Machine Commerce Observatory' leads with service branding rather than the tool's specific verb+resource.

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 concrete when-to-use guidance: 'Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo.' That is actionable context. It stops short of a 5 because it never names probe402_endpoint_grade or explains when the grade tool is the better choice.

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