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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful non-obvious context: responses are private/no-store, uploaded text is untrusted data, free read limits exist, and only publish_base exposes files publicly. Much of the remaining text is generic account policy, but the security and privacy disclosures are valuable beyond 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?

The purpose is front-loaded, but the description then dumps many account-wide policies—purchase behavior, upload/replacement publishing rules, removal effects—that are not specific to reading Markdown. For a simple two-parameter read tool, this is bloated and includes sentences that do not earn their 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?

The description covers safety, privacy, trust boundaries, and account limits, which is substantial. But for a read tool surrounded by many format-specific siblings, it omits the most important context: when to use Markdown versus original, source, docx, PDF, or image readers.

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 100%, so the schema already documents both base_id and document_id as 64-character IDs. The description adds no further parameter meaning, which is acceptable given the high schema coverage baseline.

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 first sentence, 'Download document Markdown,' states a specific verb and resource. It also partially distinguishes account scope with 'Personal-account operations,' separating it from public_ and team_ siblings. However, it does not distinguish this from the many other personal read variants such as read_base_source, read_base_original, and read_base_doc_source.

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?

The description gives account-level policy and limits but never says when to choose this tool over read_base_source, read_base_original, read_base_doc_source, or the public/team markdown readers. An agent must infer selection from the tool name alone.

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