dsb_get_delay_evidence

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld=false, so the safety profile is covered. The description adds genuine value by clarifying data provenance — the evidence is locally supplied and no rail API call occurs — which implies possible staleness and a closed data set. It stops short of describing result shape, ordering, or what an empty result means.

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?

A single front-loaded sentence with no filler; the scope qualifier and the negative constraint are both packed in without waste. It is arguably under-specified rather than over-written, but there is nothing to trim.

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?

An output schema exists, so return values need no explanation, and annotations cover safety. What remains missing for a per-journey lookup tool is any tie between the required journey_id and the returned evidence, plus minimal usage context relative to its siblings — without that, an agent knows what the tool reads but not precisely how to feed or choose it.

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 0% and the singular required parameter journey_id is never mentioned in the description, so nothing is added about what a journey ID refers to, where to obtain it, or whether evidence is returned only for that journey. With one obviously-named parameter the cost is limited, but the description does not compensate for the coverage gap.

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 uses a specific verb ('List') and a specific resource ('final-arrival evidence') and scopes it with 'locally supplied', which distinguishes it from anything that would pull live data from a rail API. It does not explicitly contrast itself with siblings like dsb_status or dsb_prepare_claim_form, and 'final-arrival evidence' is domain jargon an agent must infer means per-journey arrival records.

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?

There is no when-to-use guidance and no alternatives named. The phrase 'nothing is fetched from a rail API' hints at a use case (reading cached/held evidence rather than querying a live source), but the agent is not told which sibling to prefer when it needs live status versus stored evidence.

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