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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds substantial behavioral detail beyond that: it explains the query matching is case-insensitive and matches aliases, describes pagination behavior ('Large categories come back one page at a time'), and instructs the agent to follow nextOffset for subsequent pages. It also clarifies that offset skips entries and the order is stable. These are valuable runtime behaviors not inferable from annotations alone.

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, dense paragraph with no filler. Every sentence serves a purpose: purpose statement, category-to-ID mapping examples, browsing instruction, and pagination handling. The most important information (what it resolves and for whom) is front-loaded. It is appropriately concise for the tool's complexity.

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?

The tool has an output schema (so return format is externally defined), annotations cover safety and idempotency, and the description explains all operational nuances: category semantics, query behavior, pagination, and offset usage. There is nothing missing that an agent would need to correctly invoke this tool, even for large reference sets. The combination of schema, annotations, and description is 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?

The schema already provides 100% coverage with descriptive parameter descriptions (e.g., category enum values mapped to ID types, query pattern and alias matching). The description enhances this by giving concrete examples ('CCS' -> connectiontypeid, 'ChargePoint' -> operatorid) and explaining the relationship between offset and nextOffset for paging. This goes beyond the schema's baseline, but since the schema is already thorough, the added value is an incremental improvement rather than a necessity.

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: 'Resolve Open Charge Map reference data to the integer IDs that openchargemap_find_stations filters require.' It names the consumer tool and explicitly differentiates itself from siblings (find_stations is the target, get_station and get_station_comments are unrelated). The mapping examples further clarify the exact role.

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 clear, actionable usage context: pick a category, pass a name/code to get an ID, or omit the query to browse. It also explains pagination for large categories. However, it does not explicitly state when not to use this tool versus alternatives (e.g., 'use this only for reference lookups, not station details'), though the purpose statement makes that inference straightforward. Is it explicit enough for a 5? It names the dependent tool, so it effectively guides selection, but the lack of an explicit exclusion directive keeps it at 4.

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