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

Annotations already declare readOnly/idempotent, so the bar is lower, yet the description adds real behavior: the 128 KB per-read cap, next_offset continuation, and the header's version field that must be passed back as base_version for later writes. That concurrency-relevant detail is exactly the kind of context annotations cannot carry.

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?

Three sentences, each load-bearing: return shape first, then the partial-read modes, then the size/revision/file variants. No filler and the primary use case is front-loaded.

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 7-parameter tool with no output schema and near-zero schema coverage, the description covers the return contract, pagination, and every non-trivial parameter, so an agent can call it correctly. It stops just short of linking to sibling discovery tools or stating error behavior for missing paths.

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 only 14%, so the description must compensate, and it does: limit/offset are explained as line ranges, outline and section as alternatives for partial reads, revision as a page_history lookup, and path as sometimes an uploaded-file path returning image or document text. Only workspace is left to the schema, which already documents it.

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 specific verb and resource ('Read a page') and immediately characterizes the return: a JSON header plus markdown text. It distinguishes itself from siblings like page_history (revisions) and the write tools by being the read path, and names the header fields it produces.

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?

Gives concrete conditions for each mode: outline=true for headings/line numbers, section for one heading, offset/limit for line ranges, revision for past versions, and uploaded file paths for images or document text. It does not explicitly route the agent to list_pages/search_pages for discovering a path, which is the one missing 'when-not' linkage.

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