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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the safety profile needs no repetition. The description adds value beyond that: it states the output units and content (litres, governing rule, passing spill pallets) and the error behaviour of returning 16 region codes for an unrecognised region. It leaves the default 'mode' (bund vs tray) and the definition of a 'passing' pallet unexplained.

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?

Three sentences, front-loaded with the action and result, then prerequisites, then the failure mode. Dense but every clause carries information; the one long region enumeration is the only mildly costly stretch, though it does real work by pre-empting invalid inputs.

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 9-parameter, no-required-fields, no-output-schema calculation tool, the description covers what is computed, what is returned, required input, and error handling — enough to call it correctly. The remaining gaps are the unmentioned bund/tray mode and what the container-size parameters do, both of which the schema does cover.

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%, so every parameter is already documented, which sets the baseline at 3. The description contributes the full region enumeration ('England, Wales, ... world') and confirms that at least one of the four count parameters is required — a constraint the schema cannot express since nothing is marked required. Other semantics (mode, liquid, sizes) are left entirely to 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?

Specific verb + resource: 'Apply the secondary containment rule ... to the containers stored together, and return the minimum sump capacity in litres'. It also names the concrete return payload (capacity, governing rule, passing spill pallets), which is far more than a restatement of the name. No sibling tool (ADR points, UN packaging marks, IBC inspection dates) does anything similar, so the boundary is obvious.

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 real preconditions — 'Needs at least one container count (drums, ibcs, small or other)' — plus the fallback for an uncovered region, so an agent knows both how to call it and what happens on failure. It stops short of comparing itself to siblings or telling the caller when to prefer a different tool, which keeps it at 4 rather than 5.

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