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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the data is scoped strictly to the signed-in person's own account, requires no user-supplied figures, and the values are the filing-rule counts shown on their dashboard. It stops short of noting freshness/caching or what an empty/unfiled year looks like.

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 sentence, front-loaded with the verb and subject, then a colon-list of the returned fields. It is dense but every listed element maps to a real output field and is justified since there is no output schema. Slightly heavy as a single run-on sentence, but not padded.

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 must describe the return value, and it does so thoroughly (income, expenses, profit by filing rule, income tax and Class 4 NI, undecided transaction count, filed quarterly updates, next deadline). Annotations cover the safety profile and the schema covers the only parameter, so an agent has everything needed to call and interpret 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 the single taxYear parameter is fully documented with an enum and a stated default, so the schema carries the parameter meaning. The description never mentions that the year can be selected, adding nothing beyond the schema; baseline 3 applies when the schema does the work.

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 and resource (read the signed-in person's own account / tax year so far) and enumerates exactly what it returns, which is more than most siblings do. It distinguishes itself from the calculate_* and list_* siblings only implicitly, by framing the output as a single aggregated dashboard view rather than a computation or a raw list.

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 a usage cue – 'Needs no figures from the person: everything comes from their records' – which tells the agent it can call with no input, and by omission points away from the calculate_* tools that need figures. However, no alternative is named and no condition selects this tool over get_mtd_deadlines or list_transactions, so usage is only implied.

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