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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the 4 KiB preview cap with resource links, the 2 MiB UTF-8 markdown ceiling, truncation reporting via `result_meta.markdown`, nullable `source_truncated` for legacy metadata, the required 'requests:read' scope, and the failure envelope {ok:false,status,error}. Nothing here contradicts the annotations.

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 front-loaded correctly, starting with purpose and format branching before edge cases, and most sentences carry real information. However, it is a dense block with duplication — the omission behavior is stated twice ('Omit `format` to return HTML plus structured `data`...' and 'omission returns HTML plus available data previews') — and the markdown truncation details could be compressed.

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 supplies the return shape ({ok,status,data,meta}) and error shape, plus per-format field composition and size limits. Given a 2-parameter tool with a genuine preview-vs-full-content fork, an agent has everything needed to call it correctly and interpret the result.

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, but the description genuinely adds meaning: it explains the consequence of omitting `format` versus supplying one, what fields accompany a selected format (`id`, `format`, `result_meta`, `expires_at`), and the non-obvious constraint that `data` exists only for extraction requests. The markdown conversion algorithm (non-empty main region, else a single article, else cleaned body) further characterizes the value in a way the enum cannot.

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 opening sentence names a specific verb and resource ('Reads the retained result of one request') and the body scopes it as a metadata/preview read, which cleanly separates it from data_get_request (request state) and data_read_result_content (full content). An agent can tell what this returns 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?

It gives explicit branching: omit `format` for HTML plus structured data, specify a format to narrow the payload, and use `markdown` for agent-readable page content. It also names the alternative tool and the exact condition that selects it — 'Use `data_read_result_content` with an explicit format to read the full selected content in 16 KiB chunks by default, up to 64 KiB' — which is precisely the routing decision an agent needs.

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