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

Annotations already declare readOnly/false-destructive/non-open-world, and the description adds real context beyond that: it reads no site so no fetch occurs, text is capped at 12000 characters, references may be 'hidden' where unreadable, and 'failing' marks dead sites. This meaningfully reduces misinterpretation of a read-only retrieval.

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?

The content is dense and information-rich, but it is delivered as one long run-on sentence with a muddled opening clause, making it hard to parse. It is not padded, but structure and front-loading suffer.

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-shape burden and does so well, enumerating title, publisher, state, asOf, references, outline, text window, changedAt, editions, and failing. The main gap is absence of guidance on alternatives/siblings.

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 100%, so the baseline is 3, and the description adds value by illustrating 'find' («Article 18»), explaining 'offset' accepts a prior nextOffset or an outline entry's offset, and enumerating accepted document identifier forms. It complements rather than repeats the schema.

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 makes clear this retrieves a legal act by document id, address, or key and returns its text/metadata. The opening clause is garbled ('A legal act that issues or wiki pages you can read refer to'), but the intent — get a stored legal document — is recoverable. It does not distinguish itself from siblings like find_by_legal_document or search_legal_library.

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 usage of 'find' (land on a place) and 'offset' (read on from nextOffset), and clarifies it reads no site. But it gives no guidance on when to choose this over find_by_legal_document, search_legal_library, or list_legal_references, leaving sibling selection to inference.

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