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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that the description usefully discloses what the tool emits — a hierarchy-of-controls checklist with named coverage areas (TG20 scaffold, 7-day inspections, fragile surfaces, power lines, highway licences, hot works, asbestos, rescue), a scored likelihood x severity register, and a short printable risk note — which is real behavioral context the annotations do not carry. It stops short of stating pagination, determinism or size limits of the output.

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 core purpose is front-loaded, but the middle is a 15-item run-on parenthetical list that is hard to parse and partly duplicates the schema's enum and boolean parameters. The example call at the end earns its place; the sprawling bracket does not fully.

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 16-parameter tool with a nested object and no output schema, the description carries the necessary weight by enumerating the artifacts returned (checklist, CDM duty block, scored risk register, printable risk note). A few input flags remain unexplained, but an agent has enough to call it correctly and set expectations for the result.

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 69% across 16 parameters including a nested trade-profile object, so compensation is needed and the description does provide it: the typical call shows the two required parameters, the enum value 're_roof', and signals that eaves height, pitch, duration, worker count, access type and adjacency to a public highway meaningfully drive the checklist. It does not explain the less obvious flags (fragile_surfaces, occupied_building, asbestos_suspected, overhead_power_lines) or client_type's effect on CDM duties.

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 names a specific verb-and-artifact set (build a working-at-height/scaffold checklist, CDM 2015 duties, a scored risk register and a printable risk note) for a clearly bounded domain, and the regulatory basis (WAHR 2005, CDM 2015, HSE guidance) further pins it down. An agent can distinguish this from siblings like check_building_regs or roof_takeoff purely from the text, since it is the only one producing checklist plus risk note artifacts.

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 is only implied: the roofing-job context and the 'Typical call' example show the intended scenario, but there is no explicit statement of when to call this versus alternatives, no preconditions, and no exclusions (e.g. whether it suits non-roofing trades or when an existing plan supersedes it). The example call is helpful signal but is not a routing rule.

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