List codebook

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds one genuinely useful behavioral detail: records come back 'as UOL sends them, minus audit fields', which tells the agent the response shape is a stripped passthrough. It says nothing about ordering, caching, or size characteristics of the upstream source.

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?

Purpose is front-loaded in the first clause and the response-shape caveat is isolated in a short second sentence. The long enumerated list is somewhat run-on and partly duplicates the enum, but the glosses make the repetition earn its place. No filler or marketing language.

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 an output schema present and a simple three-parameter surface, the description covers what the agent needs: what the tool returns, that audit fields are stripped, and why each kind matters. The only gap is that it does not indicate whether results are paginated further or how to locate a specific record by ID, which a sibling lookup tool might handle.

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 67%, and the uncovered parameter is the critical 'kind' enum. The description compensates well by glossing each value, including Czech operational terms (střediska, zakázky, pokladny) and the practical note that 'products' supplies the product_id needed by invoice lines. Page/limit semantics are already documented in the schema, so no further detail is required there.

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 opens with a specific verb-plus-resource framing ('Reference data (číselníky) used by invoices and documents') and enumerates the exact kinds of reference data the tool returns. An agent can immediately tell this is a catalog/lookup tool. It does not name a sibling, but no sibling in the list overlaps with this function, so differentiation is less critical.

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 implied rather than stated: the parenthetical '(the product_id invoice lines need)' hints at the key downstream use case of fetching product IDs before building invoice lines. There is no explicit when-to-use versus when-not-to-use guidance and no mention of alternatives for looking up a single record.

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