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

Annotations already declare readOnly/idempotent/openWorld, so the bar is lower. The description adds genuinely new context: 'Measures tasks, not people' sets methodology expectations, 'ordered by the Department for Education's exposure ranking' discloses the model behind results, and 'Free, no key' states the auth requirement.

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 core purpose in the first clause, then scope caveats. It is dense and every clause carries information, though the single long run-on sentence could be split for readability.

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?

There is no output schema, but the description conveys the return shape ('full-time roles' worth of tasks') and the ranking basis, so an agent knows what to expect. Only the exact result structure (per-role breakdown vs totals) remains unspecified.

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% with clear per-role descriptions and defaults, so the schema does the heavy lifting. The description only adds that there are seven role groups, which is already visible from the schema, so baseline 3 applies.

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 output unit ('estimates how much of a team's work AI could take on today, as full-time roles' worth of tasks') plus the input basis (headcount in seven role groups). This clearly separates it from siblings like calculate_ai_savings and check_job_ai_risk.

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?

Usage context is implied by the description ('team's work', role-group headcounts), and 'Free, no key' lowers the barrier, but it never explicitly says when to prefer this over calculate_ai_savings, calculate_ai_time_saved, or check_job_ai_risk. No exclusions or prerequisites are stated.

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