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

The description earns credit beyond the annotations by disclosing two non-obvious traits: the result is persisted ('Results are saved in the user's Puley history'), which explains the otherwise puzzling readOnlyHint=false, and there is a quota rule ('The first call on a document uses one read; its other parts and searches for a day are free'). It does not say what happens at the end of a document, how errors on a bad `link` surface, or whether the free searches reset behaviour changes per document.

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 purpose, then the `part` mode, then `find`, then cost/persistence — a sensible information order with little filler. The sentence 'Results are saved in the user's Puley history' is borderline promotional but carries behavioral information; the phrase 'the next part it names' is slightly opaque on first 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?

For a three-parameter, no-output-schema read tool this covers the essentials: what it reads, how to page through, how to search within, and the cost model. The main gap is that the shape and length of a returned part (whether it echoes the next part number, includes page markers, how truncation is signalled) is only hinted at.

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 0%, so the description carries the burden and does add real meaning for `part` (start at 1, then follow the part it names) and `find` (words or a natural-language question, with examples like 'termination clause'). The required `link` parameter is never described — no format, URL vs. ID, or whether PDFs and web pages are treated differently — leaving one of three parameters undocumented.

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?

Useful specificity: a precise verb + resource ('Read a long PDF, report, annual report, filing, paper, contract or web page') plus an explicit scope rule ('Suits any document longer than a few pages') that separates it from the generic `read`/`read_site`/`see_page` siblings. It stops short of naming an alternative tool outright, so differentiation is inferred rather than stated.

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 clearly routes between the two modes of operation: use `part` to walk a document sequentially ('1 for the start, then the next part it names'), and use `find` to get 'the sections about it with their page numbers instead of a part.' What's missing is guidance on the boundary with non-long-document siblings, e.g. when a short page should go to `read_site` rather than here.

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