Publisher and books

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description contributes one genuinely new behavioral fact — a fixed page size of 16 — but says nothing about what happens with an invalid publisher slug/id, whether the description can be absent, or how cursoring terminates.

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 short sentences, front-loaded with the return content and pagination size, with no filler. The second sentence is a compressed fragment that leans on an external reference, which slightly weakens standalone readability but costs no length.

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 must convey return shape; it does so minimally (publisher description + books, 16 per page) but omits the fields of each book entry and any ordering guarantee tied to the default sort. For a 5-parameter, cursor-paginated tool this is adequate but leaves real gaps.

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 80%, so the schema already documents sort values, max_price units (Toman) and cursor usage; baseline 3 applies. The 'as in tg_browse' cross-reference delegates meaning to another tool's documentation rather than adding standalone clarification, and it does not cover the required publisher parameter (slug vs id choice) at all.

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 the resource precisely — a publisher's description plus its books — and adds a pagination fact (16 per page), which clearly separates it from siblings like tg_book (single book) and tg_author (author pages). It lacks an explicit verb, but 'X and its books' is unambiguous for a retrieval tool.

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?

There is no when-to-use or when-not-to-use guidance: nothing tells the agent to prefer tg_search or tg_book when it has a title rather than a publisher, or what to do when the publisher is unknown. The second sentence ('Sort, format, max_price as in tg_browse') is a parameter-behavior pointer, not usage guidance.

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