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

Annotations already declare a safe, idempotent, non-destructive read, so the bar is lower, and the description adds real substance: the escalation rules that raise urgency (water near electrics, bulging ceiling, vulnerable person in the cold, unstoppable water), the Northern Ireland-sensitive gas emergency number, and the two returned fields. It does not say how deep or long the advice is, or that the output is guidance rather than a guarantee.

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?

The purpose and the escalation rules are front-loaded, and the worked example at the end is a high-value addition. The main body is a single dense sentence with several chained clauses, which makes it slightly harder to scan than it needs to be.

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 12-parameter tool with a nested object and no output schema, the description covers the essentials: what advice is produced, how urgency escalates, and the shape of the returned `urgency` and `nero_work_job`. Remaining gaps are the undocumented boolean flags and the role of the trade object, which the schema itself partly covers.

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?

With only 33% schema description coverage across 12 parameters, the description carries weight and does explain the meaning of the triage booleans via the escalation list and the worked example (situation, vulnerable_people, outside_temp_c, other_heating_available, water_stopped). However, several parameters such as pipe_split, only_toilet, sewage_inside, nation and the nested trade object are never mentioned in the description, leaving them documented only thinly in the 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?

The description states a specific resource and audience: emergency triage advice for a homeowner reporting a problem, returning an `urgency` value and a ready-to-post `nero_work_job`. It also enumerates the covered situations (gas smell, CO alarm, burst, no heat) so an agent can distinguish it from sizing/record-check siblings like check_gas_record or size_heat_source.

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?

The opening clause 'For a homeowner reporting a problem' sets clear usage context, and the situation enum plus the typical-call example show what kind of input belongs here. It does not name when NOT to use it or point to a sibling alternative, so it falls short of the explicit routing a 5 requires.

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