Search wells

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

With no annotations supplied, the description carries the full behavioral burden and largely delivers: it discloses date normalization to ISO YYYY-MM-DD (or null), states that filters combine with AND, describes the returned record shape, and flags the performance cost of omitting state. It stops short of covering error behavior, rate limits, or what 'source-specific extras' concretely contain, so it's strong but not exhaustive.

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 description is a single front-loaded paragraph that leads with purpose, then normalization, then filter semantics, then the count_only usage tip. Each sentence carries distinct information and nothing is redundant with the schema. It is dense, but that density is justified for a 12-parameter tool.

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 tool with 12 parameters, no output schema, and no annotations, the description covers the essential ground: return format, date normalization, filter combination, and query sizing. Gaps include pagination semantics across multiple sources (offset/limit are only defined 'per source' in the schema) and the precise shape of multi-source results, which an agent would want when aggregating.

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 100% with inline examples (e.g. 'Fervo', 'California Resources', 'CA-GEO'), so the schema already documents every parameter well. The description adds global semantics that enrich parameter understanding — AND-combination of filters and date normalization across returned fields — but does not extend per-parameter meaning beyond the schema. Baseline 3 is appropriate.

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 opens with a specific verb and resource ('Search state regulator well databases') and enumerates the exact search dimensions (operator, well/lease name, county, field, status, type). It further differentiates from get_well via the api parameter note ('For cross-state API lookup use get_well instead'), which explicitly carves out the sibling's territory. An agent can immediately tell what this tool does and how it relates to get_well.

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 concrete usage direction: the api param steers exact API lookups to get_well, the state param advises preferring a state code to avoid slower all-state searches, and count_only is positioned as a way to size a query before pulling records. It does not, however, address when to reach for spatial sibling wells_near or raw_query over this tool, leaving part of the alternative routing implicit.

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