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

Annotations already provide the safety profile (readOnlyHint=true, destructiveHint=false), but the description adds zero behavioral context on top: no pagination semantics, no filter/orderBy capability, no note about paged results being a list. There is no contradiction with annotations, but the description carries no behavioral load.

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?

The description is a single short sentence with no dead weight, so it is efficient. But it is so terse it mostly restates the title 'List Accounts' plus the acronym, and for a tool with eight parameters and many siblings it comes across as under-specification rather than tight writing.

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 eight parameters, no output schema, and a large sibling family, the description tells an agent nothing about what an 'account' is, what the returned list contains, how the OData/pagination params interact, or any prerequisites. The schema fills in some gaps (connectionRef instructions are useful), but the description itself leaves nearly all context empty. An agent selecting between this and ~20 other list_* tools has insufficient information.

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 only 50%, and the four least-documented parameters (top, page, skip, pageSize) are pagination controls that the description entirely ignores. The sentence 'Lists -BRC accounts' adds no meaning beyond the schema descriptions that already exist for companyName, connectionRef, filter, and orderBy.

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 states a verb and resource ('Lists BRC accounts'), so it is not a pure tautology. However, 'accounts' is ambiguous given the sibling set, which includes brc_list_nominal_accounts, brc_list_bank_accounts, and brc_list_customer_account_trans; the description gives no indication of which account type this covers, only adding 'BRC' on top of the title.

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?

No guidance exists on when to use this tool versus alternatives or what precursor steps are required (e.g., whether a company connection must be confirmed first). The agent gets nothing to disambiguate it from the many other list_* siblings.

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