SMB Compare

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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real context beyond that: it computes from the user's own calculator values and returns comparison-table links, provider pages, and quote links where available.

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-loads the core behaviour (rank by cost) and the geography, then appends illustrative examples. No padding, though the example list is slightly long relative to the rest.

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 read-only tool with no output schema and a nested inputs object, the description covers what it computes, what it returns, and the supported markets. It omits how rankings are presented (ordering, result count) and the defaulting/ignored-input behavior, which is left to the schema.

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?

With 100% schema coverage the baseline is 3, but the description earns a step up by explaining what the generic 'inputs' object represents (card volume, average sale, employees, users) and by naming the three supported markets, giving meaning beyond the slug-only schema docs.

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 ('Ranks providers in a category by estimated monthly cost'), plus the scoping constraint (user's own numbers, US/UK/AU). An agent can distinguish it from the only sibling, list_categories, 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?

Concrete examples ('EFTPOS and card machine fees', 'cheapest payroll software', 'POS system costs') make the intended context clear, and the schema routes category slugs to list_categories. It stops short of explicitly stating when NOT to use it or naming list_categories as a prerequisite step in the description itself.

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

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

Annotations already establish the safe read-only, closed-world profile, so the bar is lower. The description goes further by disclosing the return shape: categories per country, whether quotes are available, and the per-category calculator inputs. It does not mention caching, ordering, or pagination, but for a small enum-driven list that is a minor 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?

Two tight sentences, front-loaded with what is listed and scoped by country, followed by the payload detail. No filler or redundancy.

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 no output schema, the description carries the return-value burden and does describe the content of each category entry, including quote availability and valid calculator inputs. The main omission is any explicit sequencing guidance relative to compare.

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?

Only one parameter with 100% schema coverage and an explicit enum ('The user's country: US, UK or AU'). The description restates the same three values without adding format or default details, so it neither helps nor hurts beyond the schema baseline of 3.

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 ('Lists the business software and merchant services categories') plus the scoping dimension (country) and what each entry contains. It references the sibling compare and its calculator inputs, giving a soft differentiation, but never explicitly says how this differs in role from calling compare directly.

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: mentioning that each category lists the inputs compare accepts hints this is a discovery/prerequisite step before compare, but there is no explicit when-to-use, when-not, or 'call this first' instruction.

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