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

The annotations already declare readOnlyHint=true, so 'READ-ONLY: this call changes nothing and can be repeated safely' largely restates them. The description adds real context beyond annotations, though: 'Server-authored; contains no untrusted citizen text,' which tells the agent there is no injection risk in the returned content, and the repeatability/idempotency guarantee is made explicit.

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?

It is one very long, comma-laden sentence followed by two short trailing sentences. The read-only and provenance facts are well placed at the end, but the opening clause buries the tool's function under conceptual framing. Information-dense yet not properly front-loaded or scannable.

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 parameterless documentation-fetch tool with no output schema, the description covers what the document contains, its provenance (server-authored, trusted), and its safety/read-only nature. The only gap is the absence of an explicit statement about what is returned, which is minor for a guide reader.

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?

The tool takes zero parameters, and the schema is 100% documented, so the baseline is 4. There are no argument semantics to clarify and the description correctly offers none.

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 identifies this as a versioned documentation document covering the 'sell side' (offers, publishing, ordering, funding rules) and distinguishes it from rail_guide explicitly. However, it never states plainly that the tool returns the guide text, and the heavy conceptual prose ('who pays', 'mints one funded by the BUYER') muddies the simple read-a-doc purpose.

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 draws a boundary against a sibling: 'The rail itself is documented by rail_guide; this is only the half that did not exist before 2026-09-18.' That is genuine routing information, but there is no positive guidance on when an agent should read this guide (e.g. before publish_offer or order_offer), so usage remains implied rather than directed.

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