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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds two things the annotations do not: results are cached for ten minutes, and the payload can include an external catalogue document fetched from /.well-known/ptpge/catalogue.json. That caching note is genuinely useful for an agent planning repeat queries.

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 resource and scope, then the filtering mechanics, then read-only/cache traits. It is a dense couple of sentences with parenthetical examples that earn their place, though the catalogue aside slightly interrupts the filtering instructions.

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 so: it says each maker comes with its making term and optionally its own catalogue with press models and paper series. Combined with three simple flat parameters and full annotations, an agent has enough to call it correctly; only explicit sibling routing is missing.

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%, with `limit` undocumented but bounded by min/max/default in the schema. The description compensates by explaining that `makes` accepts a term path or slug and giving concrete slug examples (printing-presses, wide-format-printers, paper), plus clarifying that `text` matches name and definition — meaning beyond the schema's own one-liners.

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 names a specific verb+resource ('Makers in the PTPGE supplier register') and enumerates what the resource covers (press and equipment builders, paper mills), plus what each record contains (a making term and, when claimed, the maker's own catalogue). It is clearly a finder for makers, but it does not name the closest sibling (ptpge_find_vendors) to contrast scope, so it stops short of 5.

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 tells the agent how to narrow results ('Filter by `makes` ... or free text') and that there is a ten-minute cache, which implies repeated calls are cheap. It never states when to prefer this over ptpge_find_vendors or ptpge_search_terms, so the routing decision is left implicit.

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