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

Annotations already declare non-read-only, idempotent, non-destructive, and the description adds genuinely new behavioral facts: the saved rules override the inferred house style, an empty string clears them, and there is a 4,000-character ceiling. Overwrite semantics are consistent with idempotentHint=true and with destructiveHint=false, since clearing a rules field is an intentional replacement rather than data loss. It does not say whether existing generated items are retroactively affected, which is the one notable omission.

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 tight sentences, front-loaded with the core action and followed by the precedence rule and the clearing rule. The trailing 'Up to 4,000 characters' duplicates the schema's maxLength=4000 and is the only sentence that does not fully earn its 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?

For a small 4-parameter mutation with no output schema and full schema coverage, the description supplies what structured fields cannot: override precedence, clearing behavior, and scope to AI-written content. It leaves unaddressed whether the owner needs a particular permission and whether previously generated drafts are re-evaluated, minor gaps for this tool's size.

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 baseline is 3, but the description goes further by explaining the precedence semantics of 'guidelines' relative to the learned house style and by signaling that 'collection_type' is usually 'blog'. That adds authoring guidance beyond the schema's 'The guidelines, in the owner's words.' The 4,000-character note merely repeats maxLength, which caps the credit.

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 ('Save the owner's rules for new AI-written items in one collection') and enumerates the content dimension: length, tone, sections, required inclusions, cover look. No sibling tool in the list manipulates per-collection writing guidelines, so the boundary is unambiguous even without naming an alternative.

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 clear operating context — these rules apply to new AI-written items and take precedence over the house style Mondovo infers from published items — plus the clearing behavior via empty string. It stops short of naming a sibling to use instead (e.g. when to edit items directly vs. set global rules), so it is clear context without explicit exclusions.

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