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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description's 'Read-only' claim is consistent with them — no contradiction. The description adds domain-specific context beyond the annotations: 'never creates a checkout or payment obligation' disambiguates this read-only getter from checkout-creating siblings like prepare_site_report_checkout, which is genuinely useful behavioral information. It does not describe any other behavioral traits, but for a simple getter this is adequate.

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?

Three sentences with zero filler: the first front-loads the trigger condition, the second guards against misuse, the third guarantees side-effect safety. Every sentence carries unique information and the most decision-relevant content (when to use) comes first.

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 zero-parameter tool whose safety profile is fully covered by annotations, the description is nearly complete: it covers when to use, when not to use, and side-effect behavior. The remaining gaps are minor — the alternative sibling is implied rather than named, and since there is no output schema, the return shape of 'offers' is not described.

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 input schema has zero parameters and schema coverage is 100%, so the baseline of 4 applies. The description adds a small but useful semantic note: the tool depends on a prior site-screen context rather than explicit arguments, reinforcing why it should not be called first.

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 identifies a specific resource ('pricing or paid AliEV options') and the title concretizes it as 'paid-depth options,' so the purpose is clear and not a tautology. It also begins to distinguish itself from sibling tools by stating it is not the first tool for address-based property queries. However, the exact contents of a 'paid-depth option' (e.g., price tiers, upgrade paths) are never specified, so the resource semantics stay slightly vague.

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?

The description gives explicit sequencing ('Use AFTER a site screen'), an explicit trigger condition ('when the human explicitly asks for pricing'), and a clear exclusion ('Do not use this as the first tool for a property-specific EV question when an address is available'). It stops short of a 5 because no sibling is named directly — the alternative for address-based questions is implied (analyze_ev_site) rather than stated.

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