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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. However, the description discloses no behavioral traits beyond that: nothing about not-found behavior, dependence on a prior confirmed connection, or whether the returned customer is the full object. The interesting connectionRef reuse guidance lives in the parameter schema, not the tool description.

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?

One short, front-loaded sentence: 'Gets one BRC customer by id.' Nothing is repeated from the title and there is zero filler, so every word earns its place. For the size of a simple read tool, this is ideal.

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, single-record read with full schema coverage and suitable annotations, the essentials for invoking it correctly are present. Missing are usage context among the many get/list siblings and any mention of required preconditions (such as a connection), and because there is no output schema the tool description could have disclosed what to expect in the response. The tool is callable, but the description glosses over context.

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%: 'id' and 'companyName' both have explanatory descriptions and 'connectionRef' carries a thorough explanation about reuse, session-id rotation, and that it is not a credential. With full schema coverage, the description is not required to add parameter detail; it neither helps nor hurts beyond the baseline.

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 names a specific verb ('Gets'), a concrete resource ('BRC customer'), and a selection method ('by id'), which separates it clearly from list_customers and create/update/delete_customer siblings. It does not explicitly disambiguate from brc_get_customer_opening_balance or brc_get_customer_account_trans, but its single-record intent is unambiguous.

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 statement about when to use this tool versus alternatives. It does not say 'use this when you have a customer id (unlike brc_list_customers when you need multiple)' nor does it warn against using it when a connection has not been confirmed. Usage is only implied by the tool name and the word 'by id'.

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