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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description adds genuinely new context about conditional field presence ('when the edition publishes it', 'when the edition carries it') and explicitly states the plug flag 'changes no outcome, count or cost', which prevents an agent from misreading it as an authoritative plug determination. It stops short of describing not-found or error 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 lead clause is well front-loaded, but the body is one sprawling sentence that enumerates roughly a dozen return fields. Since an output schema exists, that enumeration largely duplicates structured data and inflates the description at the cost of scannability.

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 an output schema present, the description need not document return values, yet it does so thoroughly and adds the conditional-presence and plug-flag caveats that matter for interpretation. The only real omission is behavior on an unknown or malformed API number.

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 the api parameter's description already spells out the eight-digit, no-42-prefix, no-dashes format. The description restates the same constraint ('county code + unique number, no 42 state prefix') without adding new syntax or edge cases, so it neither compensates nor detracts — baseline 3 applies.

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?

States a specific verb and resource — returns one wellbore's screening record keyed by API number — and anchors it to the Inactive Well Aging Report, which separates it from get_plug_record and get_operator_exposure without needing to open a schema. The record's domain (screening outcome, operator evaluations, plugging cost) is concrete enough to distinguish it from every sibling.

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?

Usage is implied rather than stated: the single-record, API-keyed lookup shape makes it obvious this is a point retrieval, and the note that the plug flag is only a cross-check hints at get_plug_record's role. But there is no explicit 'use this when…' or 'for plug details use X instead' routing, and nothing about what to do when the API is not found.

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