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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond that: the credit cost, the upstream source (Historic England NHLE), the legal-offence context that motivates lookups, and an important data caveat that the position is a reference point and not the restricted-area boundary. It does not describe result ordering or pagination behaviour, which keeps it below a 5.

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?

Front-loads the resource and scope, then moves through returned fields, audience, source, caveats and cost in a logical order with no filler sentences. It is dense rather than bloated, though the trailing parenthetical cost note and the legal sentence sit awkwardly in one unbroken block that would read better split.

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 carries the burden of describing return values and does so by naming the fields returned. For a two-parameter read-only lookup, the combination of scope limits, data source, positional caveat and credit cost leaves nothing an agent needs missing before calling 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 100% and both parameters are already documented there, including the 'omit to list all' behaviour for name and the 1-100 range with default 25 for limit. The description adds no matching semantics, spelling/tokenisation hints, or search behaviour for partial names, so baseline 3 applies.

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?

States a specific verb pair ('List or search') and a precise resource ('wrecks designated under the Protection of Wrecks Act 1973 in English waters'), then enumerates the returned fields (name, designation date, restricted area hectares, position, official link). It also explicitly bounds the dataset against near-neighbours ('not all wrecks or military remains'), so an agent can separate it from sibling heritage tools like battlefield_search or scheduled_monument_search.

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?

Gives a concrete use context ('divers and boat users check here') and an explicit exclusion ('covers designated wrecks only, not all wrecks or military remains'). What it lacks is any explicit routing to alternative tools for non-designated wrecks or military remains, so the agent must infer the alternative rather than being named one.

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