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

Annotations already declare this a safe, read-only, idempotent, closed-world call, so the description adds genuine context beyond them: the triage policy ('any danger to people makes it an emergency'), the three-speed output vocabulary, and the escalation contacts. It does not explain how the boolean flags are weighted in the urgency decision, which is the main behavioral gap.

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 routing signal (the symptom list), then the return contract, then a concrete example — a sensible order. The long trigger enumeration is dense but each item earns its place as a retrieval cue; the parenthetical about 'the same three speeds Nero Work uses' is the only sentence that adds little for an outside caller.

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 15 parameters, a nested trade object and no output schema, the description carries the return explanation itself — urgency, reasons, safe_first_steps, who to call, and follow-up questions — which is what an agent needs to decide to call it. The remaining gap is that it never says the trade object is optional or how the flags combine, though the schema covers the trade object's fields in detail.

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 only 27%, so the description must compensate and it partly does: it enumerates the problem categories matching the enum and demonstrates one combined input in the example. However, most of the danger-signal booleans (gas_smell, debris_falling, getting_worse_quickly, doors_or_windows_sticking_recently) are left to their names, with no statement of how each one shifts the urgency verdict.

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 scope — 'first-response triage' — and enumerates the exact structural symptoms it covers (crack, bulging wall, ceiling collapse, storm damage, subsidence signs) plus the ten incident classes. An agent can distinguish this from the regulatory siblings like cdm_duties or check_building_regs without opening a schema.

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 a clear triggering condition: 'when a customer reports' one of the listed problems, and frames it as first-response rather than follow-up work. It does not explicitly exclude cases or name which sibling handles the follow-on steps (e.g. party_wall_notices, cdm_duties), so it stops short of a full when/when-not statement.

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