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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower. The description adds real value on top: cursor-based pagination behavior and precise domain semantics for each returned field ('At most 5 minutes late', 'early counted as 0'), which the agent cannot infer from structure 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?

Dense and front-loaded: pagination instruction immediately follows the purpose, then field definitions. The opening sentence duplicates the title verbatim, which is mildly redundant, but the remaining text earns its place.

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 no output schema, the description correctly carries the return-record documentation and does so thoroughly. It does not state data provenance or coverage (seasonal span, geography implied by the Cst example), but for an 8-param list endpoint the essential calling information is present.

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 every parameter including cursor, limit, and the filter variants is already documented in the schema. The description repeats the cursor behavior but adds no semantics beyond the schema, making the baseline 3 correct.

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?

Clear statement of the resource and granularity ('Train punctuality per station and day') with the return shape made explicit ('Returns a list of records'). However, it never distinguishes itself from the sibling train_punctuality_daily, which an agent must choose between, so it earns a 4 rather than a 5.

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 pagination mechanics ('pass next_cursor to get the next page') but no tool-selection guidance at all. It never says when to prefer this over train_punctuality_daily, nor when filtered vs unfiltered queries are appropriate.

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