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

The annotation set exposes only a title, so the description carries the full disclosure burden. It does this well: it reveals the data source (Bus Open Data Service, England), the real-time nature of the data, and — critically — the semantic caveat that this is live position, not a prediction, preventing misuse for arrival-time queries. Limitations like rate-limits or auth requirements are not covered, but they are minor for a read-only data lookup.

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 tightly-constructed sentences, each earning its place: the front-loaded value proposition, the data-scope specifics, and the closing caveat. The opening is memorable and informative, and there's zero filler or repetition — an exemplar of concise technical exposition.

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 low-complexity, read-only lookup tool with no required parameters, no enums, and no nested objects, the description covers the essentials: what it lists, output ordering, geographical scope, data source, and the key semantic caveat. An explicit note about output structure would push it to a 5, but the description is largely complete for an agent to use it correctly.

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%, with each of the four parameters well-documented in the schema (including useful defaults like 'default 2, most 25' for within_km). The description adds the output-ordering detail 'nearest first' but otherwise does not need to and does not try to repeat schema content. This is exactly the baseline-3 scenario: schema does the heavy lifting and the description is not penalized.

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?

Uses a specific verb phrase ('Where the buses actually are near a point right now') to convey list-real-time-positions with a specific scope (England, Bus Open Data Service). The 'position rather than prediction' clause distinguishes it from sibling transit data tools without naming them, and the mention of output fields (line, heading, distance) makes the purpose concrete.

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 when-to-use context ('near a point right now'), geographic scope (England), and a when-not-to crafting caveat ('position rather than prediction') that prevents agents from misusing it for ETA-style arrival predictions. However, no sibling tool is ever named explicitly as an alternative (e.g., transit_arrivals, transit_trains), so it falls just short of the 5 bar, which expects named alternatives.

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