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

Annotations only say readOnlyHint=true and openWorldHint=false; the description goes far beyond them, disclosing cost ($0.02 per calculation / 0.02 USDC), that inputs are not stored, a 3-call-per-IP-per-UTC-day free allowance shared with HTTP trials, that a non-x402 MCP client cannot complete a paid continuation, and explicit stop/retry semantics via _meta['x402/payment']. It also states the results are illustrative and not live, and warns against silent free-to-paid fallback and automatic retries on unknown outcomes — exactly the operational hazards an agent needs.

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 is correctly front-loaded in sentence one, and the input/output examples are useful. But roughly two-thirds of the text is payment and legal boilerplate, and the output excerpt is presented twice with redundant disclaimers ('Illustrative output excerpt...' repeated), which dilutes the signal an agent needs to decide and call.

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 read-only calculation with no output schema, the description does supply an illustrative output shape (daily_energy_wh.battery_side, pv.minimum_nameplate_watts, assumptions flags), plus the nested-argument example, so an agent knows roughly what comes back. Remaining gaps are per-field semantics for panel_watts and inverter_efficiency rather than anything about behavior or return values.

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% (only a bare example sits in the schema's description field), so the description must carry the load; it partially does by naming loads, peak sun hours, PV losses and optional battery assumptions, and by giving a concrete nested example. But panel_watts and inverter_efficiency appear only in the example or not at all, and nothing explains units or meaning for peak_sun_hours or how load watts/quantity interact. Partial compensation, not full.

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 first sentence names a specific artifact ('Off-grid PV energy-balance estimate') and the computation it performs (loads + peak sun hours + PV losses -> energy balance). It also states explicit non-scope (no location/weather lookup, electrical design, surge or installation certification), which prevents the common misread of this as a full design tool. It does not name a sibling alternative, but the sibling set (endpoint/listing/payment checks) is so far from this domain that no differentiation is needed.

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 lists the inputs to supply and marks the battery assumptions as optional, which implies the calling context, and the exclusion sentence rules out weather/location-based sizing. However, it never states positively when an agent should reach for this tool versus reasoning about PV sizing itself, nor what result to expect from omitting battery versus providing it. The lengthy payment procedure is 'how to pay', not 'when to use'.

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