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

Annotations only cover idempotency and non-destructiveness; the description adds the material side effect that privacy-policy and account-deletion kinds make a hosted page live at a public URL, while other kinds merely store text. That public-exposure consequence is exactly the kind of behavior an agent cannot infer from the structured fields.

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 front-loaded sentences: the core action and precondition first, then the kind-dependent effect, then the update trigger. No filler or restatement of the name.

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 3-parameter mutation tool with no output schema, it covers precondition, side effects, and repeat-call semantics. It omits error/failure behavior and whether an already-published document can be retracted, which keeps it short of full completeness.

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 67% (app_token and markdown are documented, kind is an undescribed enum). The description compensates by explaining what the kind values actually do behaviorally and by implying markdown must be the finalized text with placeholders resolved.

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+resource ('Saves the final version of a document') and then refines it by kind, so an agent knows exactly what changes state. Siblings (audit_app, create_checkout, get_order) are unrelated, so no differentiation is required.

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 a clear precondition (every [CONFIRM: ...] placeholder resolved with the user) and an explicit re-invocation rule ('Call it again whenever the text needs an update'). It does not name an alternative tool, but no sibling overlaps this function, so the omission is low-cost.

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