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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds the meaningful behavioral nuance that a configured salary with zero payroll runs means no payment went through payroll, but says nothing about empty results, multi-company ambiguity, or pagination/limits.

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-loaded with the concrete return payload before any usage guidance, which is the right ordering. The final sentence is long and carries cross-tool orchestration plus a tax-year-free interpretation rule, which is useful but slightly bloats an otherwise tight definition.

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 compensates by naming the three returned values, and it covers the zero-payroll edge case that would otherwise confuse an agent. Minor gap remains around multi-company selection behavior, though that is largely delegated to the schema.

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 (company, tax_year) are documented there with defaults and a pointer to list_companies. The description adds no syntax, format, or edge-case detail for either parameter, so it sits at the baseline for a fully documented schema.

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 (get) and resource (payroll summary) and enumerates exactly what comes back: YTD figures, last run date, next payment due. That clearly separates it from get_transactions (bank flows) and list_employees (configured salary), which the description names explicitly.

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 the triggering user questions ('payroll costs', 'total salary spend', 'when the next payroll run is') and then an explicit multi-tool recipe for the ambiguous 'what have I paid myself' case, including the interpretation rule when payroll has never run. When-to-use and how-to-combine are both spelled out.

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