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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses genuinely valuable behavior: every read re-checks publication status, private/withdrawn bases yield a 404, and withdrawn content is never served from cache. It also carries a prompt-injection warning about treating uploaded text as untrusted data, which no structured field expresses.

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 sentences about publication checks, 404 behavior, and the untrusted-content warning are front-loaded and earn their place. The trailing iframe/search-route sentence ('3–160 search characters, at most 20 results per page') describes search constraints that belong to a different surface and reads as tangential bloat for a document-fetch tool.

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the description does state the return content ('Markdown and metadata') and covers the failure mode (404 for private/withdrawn) and the security posture, which is enough for an agent to call it correctly. It stops short of describing response structure or size limits, which would be expected for a document-returning tool.

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% and both parameters (base_id, document_id) are already documented as 64-character IDs in the schema, so the description need not compensate. It adds no format, source, or lookup guidance for either parameter, so the baseline 3 applies.

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 the document Markdown and metadata') and scopes it to published bases, so the agent knows exactly what it retrieves. It does not, however, differentiate itself from close siblings such as public_read_base_markdown or public_get_base, which an agent must disambiguate by other means.

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?

'Published bases only. No account required.' implies the access context, and the embed/iframe sentence hints at a secondary use case. But there is no explicit when-to-use-this-vs-a-sibling guidance, no stated prerequisites beyond 'no account', and no exclusions relative to the many other public_read_* tools.

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