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

readOnlyHint=true already covers the safety profile, so the description's added value is pagination mechanics ("Paged: pass next_page as page") and the shape of returned records. That is genuine context beyond the annotations, though it omits any note on auth scoping or default result volume.

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 dense sentences with no filler: resource and returned fields first, then search semantics, then paging, then the endpoint. Nothing needs to be re-read.

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 burden of describing returns, and it does list the record fields plus the next_page pagination token. It stops short of describing the response envelope or paging limits, but an agent has enough to call and consume the tool 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 75%, so the baseline is 3. The description clarifies that the search term covers name/SKU/description, but price_from, price_to, direction, and in_stock_only receive no added meaning beyond their schema entries, and the sku clause merely restates the schema's "Search by SKU."

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 ("List warehouse items") and enumerates the returned fields (name, SKU, unit, price, VAT, quantity in stock), which clearly separates it from the singular superfaktura_get_stock_item and from superfaktura_list_stock_movements. An agent can route to it without opening the 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?

It explains the two search entry points ("search matches name, SKU and description; sku matches the SKU") and hints at paging, so usage is implied. But it never states when to prefer this list tool over get_stock_item or list_stock_movements, and gives no exclusions or prerequisites.

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