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

Annotations only declare a safe read operation; the description adds host-dependent rendering (claude.ai/Desktop/mobile get the live view, text-only hosts get a share link), the interactive edit-and-save behavior, and immediate share-link propagation — all beyond what annotations provide.

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?

Front-loaded with the core action, then usage and exclusions; dense but every clause carries functional information. Slightly run-on, which keeps it from a 5.

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 still tells the agent what the caller will see (live doc, edit capability, or a share link in text-only hosts) and how it relates to sibling tools, leaving no operational gap.

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 slug/account/doc_name are already documented. The description only lightly reinforces slug's ability to accept a share URL; baseline 3 applies since the schema carries the parameter detail.

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 (open/show) and resource (doc) plus the mode ('live view of the page' inside chat), immediately distinguishing it from read-only siblings like get_doc_html or app_read_doc.

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?

Explicitly names when to call it (see/preview/check/hand-edit, or when a doc.farm link is pasted) and when not to (do not call straight after host_html_content, patch_doc, or duplicate_doc, which already show the view). This is exactly the routing guidance an agent needs.

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