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

With no annotations, the description carries the full burden and does substantial work: it discloses database-side slicing to a hard ≤2,500 token ceiling, that full text is paged by offset, that a missing view returns empty plus a reason rather than erroring, and the cost ('Free · 1 credit'). It does not mention auth requirements or whether repeated fetches are cached/cheap, so it stops short of full transparency.

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 core ('Read one view by its hp:// pointer') is front-loaded and the trailing failure case and pricing are well placed. But the middle is a sprawling em-dash run-on enumerating eight content kinds and their pointer syntaxes, which frays readability and bloats a single sentence past the point where every clause earns its place.

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 4-parameter read tool with no output schema and no annotations, the description covers addressing, truncation, paging, fallback language behavior, failure semantics, and cost — enough to invoke correctly. What remains is minor: no example of a concrete hp:// pointer string and no statement of the response envelope beyond 'empty with a reason'.

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 only 50% (uri and max_tokens have no schema descriptions), and the description compensates well: it defines uri as an hp:// pointer with enumerated valid pointer fragments, explains max_tokens as a server-side truncation cap, and clarifies offset as 'Full text only'. The lang fallback semantics are stated in the schema, not the description, which is the only real gap.

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?

States a precise verb+resource ('Read one view') and pins down the addressing scheme ('by its hp:// pointer'), plus names the two legitimate sources of that pointer (list_views, expert_ask citation). An agent can immediately tell this apart from list_views and from the search/graph siblings without opening the schema.

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?

Routing is explicit for provenance: get the pointer from list_views or from an expert_ask citation, then fetch it here. It also documents the miss case ('A missing view comes back empty with a reason'), so the agent knows failure is non-fatal. It doesn't state any when-not-to-use condition or contrast with a sibling in behavioral terms, which keeps it below 5.

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