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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: it includes unavailable stations, empty query lists all, results are ID-sorted, and pagination follows next_offset until null. This is useful operational detail that annotations don't provide.

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, dense with information, and the most important facts are front-loaded: what it finds, the scope, and key behaviors. No filler, and every sentence carries operational value. The pagination instruction is a natural final sentence.

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 description is quite complete given the rich annotations and 100% schema coverage. It covers filtering, ordering, pagination, and inclusion of unavailable stations. It stops short of describing the output schema (but an output schema exists, so that's acceptable per rubric). A small gap: no explicit statement that the tool is read-only, but annotations cover that. Overall, minor missing detail like whether 'full backend catalog' means all stations including system-hidden ones, but that's close to nitpicking.

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%, so the schema fully documents the three parameters. However, since there are no required parameters, the description could have added nuance about how query interacts with limit/offset, e.g., whether offset is per-query or per-full-catalog. It does clarify 'Empty query lists all' and 'ID-sorted', which helps understand offset semantics, but it doesn't add much beyond the schema descriptions.

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 says exactly what the tool does: 'Find stations in Bizzy's full backend catalog by name or location, including unavailable stations.' It names the resource (stations in the full catalog), the searchable dimensions (name or location), and an important scope detail (includes unavailable stations). It also implies a list/search distinction from the sibling get_station, which presumably retrieves a single station.

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 gives clear context for when to use this tool: when searching the full catalog by name or location. It doesn't explicitly name alternatives or exclusion conditions, but the sibling names (get_station, get_bizzy_info) plus the 'full backend catalog' phrasing imply this is the search/list tool vs. a single-record getter. A slight gap is not stating 'use get_station when you already have a station ID'.

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