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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is low; the description still adds genuinely new context: it returns a banded breakdown, total tax and effective rate, uses current 2026 bands, and discloses the authoritative source (Fox Davidson, FCA FRN 1056214). It does not flag that results are estimates rather than formal tax advice, which is the one behavioral caveat an agent would want.

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 action and the jurisdictions, then the covered scenarios, then the return shape, then the trigger sentence — a sensible order. The vendor/FCA attribution sentence is marketing-flavoured but does carry authority information, so it earns a marginal place; the long run-on enumeration of surcharges is dense but not padded.

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 three-parameter, no-output-schema calculator the description covers what is computed, which regimes and surcharges apply, and what comes back (banded breakdown, total, effective rate). With annotations carrying the safety profile and the schema carrying parameter detail, an agent has everything needed to call this correctly.

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 description coverage is 100% and the enum descriptions already spell out what each buyer_type and region value does, so the description is largely restating the schema's own semantics. It does clarify cross-field interaction (17% corporate flat rate only above GBP 500k and only in England/NI; no Welsh FTB relief), which is mild added value rather than a re-derivation of parameter meaning.

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+resource ('Calculate UK stamp duty on a property purchase') and enumerates the exact regimes it covers (SDLT/LBTT/LTT), reliefs and surcharges. Nothing in the sibling list (bridging, BTL stress, development appraisal, HNW qualification) overlaps, and the description makes that separation 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?

Explicit trigger list: 'Use when a user asks about stamp duty, SDLT, LBTT, LTT, additional dwelling surcharge, ADS, first-time buyer relief, non-resident surcharge, or tax on a specific UK property purchase.' That is strong positive routing, but it names no exclusions or alternative tool to prefer (e.g., for non-UK or commercial multi-dwelling cases), so it stops short of a 5.

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