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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and an output schema exists, so the safety and return-value burden is lifted. The description adds only 'Returns true hourly cost', which is redundant with the output schema, and no computation assumptions (e.g., how charges_pct is applied).

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 and short, which is good, but the 'Inputs:' sentence restates schema fields incorrectly and therefore does not earn its place. The list_bundles pointer is useful cross-referencing but sits at the tail.

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 simple three-parameter calculator with a full output schema and annotations, the description is nearly sufficient. However, the annual-vs-monthly input mismatch and the unspecified treatment of charges_pct/work_days leave the agent with an incorrect mental model of the required inputs.

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 coverage is 100% (baseline 3), but the description's input list actively contradicts the schema: it says 'monthly salary' when the required parameter is annual_gross (annual gross salary EUR), and 'billable hours/month' when the parameter is work_days (working days/year). This misleads the agent about required input units and time base.

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: 'Compute fully-loaded hourly cost-to-company', which is unambiguous. It does not differentiate itself from close siblings such as calculate_employer_cost_fr, calculate_french_salary, or calculate_salary_hourly_to_annual (the inverse operation), so an agent must guess between them.

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?

'Use for project pricing or freelance rate' gives an implied context but no explicit when-not or named alternative. The sibling set contains several near-duplicate salary/cost calculators, and the description only points to list_bundles rather than routing the agent to the correct sibling.

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