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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description adds only that matching spans "all categories," which tells the agent the search is not category-scoped; it says nothing about result ranking, result caps, or whether multiple matches or zero matches are returned.

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?

Two tight sentences, zero filler. The when-to-use condition is front-loaded before the return behavior, which is the right order for an agent scanning for routing signals.

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 simple three-parameter read tool with full schema coverage, full annotations, and no output schema, the description covers purpose, trigger condition, and result scope adequately. It stops short of describing what a match looks like or how many come back, which is the one remaining gap an agent might care about.

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 each parameter carries a meaningful description, including a cross-reference to list_companies for the company argument. The description's only added semantic is "by keyword," which is a marginal clarification of the query parameter beyond what the schema already says.

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 resource ("Search UK tax knowledge by keyword") and clarifies the result scope ("matching tax facts across all categories"). It implicitly differentiates itself from direct-lookup siblings by saying it's for when you're "unsure which category/item to look up," but it never names get_tax_facts or lookup_tax_rule explicitly, so the separation is inferred rather than stated.

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?

"when unsure which category/item to look up" gives a clear triggering condition for this tool over a targeted lookup. What's missing is the flip side — no explicit "use get_tax_facts when you already know the category" exclusion naming the alternative.

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