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

Annotations only cover readOnly/destructive/idempotent/openWorld flags, but the description adds what actually matters here: notes are private and never emailed, appear in the owner's report tagged 'AI review', replacePrevious resolves rather than deletes prior notes, unknown sections are skipped not fatal, and the response lists valid section names. It also declares untrusted-content handling. This is well beyond the annotation bar.

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?

Purpose is front-loaded and a 'How to use it:' marker structures the guidance. It is long, but nearly every sentence carries a distinct rule; only minor length cost 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?

Despite no output schema, the description explains return behavior (unknown sections listed with valid names for retry) and covers the full write/mutation contract, constraints, and safety. An agent has everything needed to invoke it correctly.

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 80% (baseline 3), and the description adds real meaning: it defines the severity levels (issue/suggestion/info) that the enum leaves bare, clarifies section anchoring must be copied exactly from headings, and explains replacePrevious's resolve-not-delete semantics. Some limits (400/600 chars) restate the schema, so just short of a 5.

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 — review a published page and leave private notes for its owner, anchored to sections — and clearly distinguishes itself from sibling tools like get_page (read) and resolve_note (owner action). An agent can tell exactly what this does without opening the schema.

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 explicit preconditions ('call get_page first and read the whole page'), a re-review trigger ('Set replacePrevious true when re-reviewing a revised draft'), and constraints ('Pro only', 'Requires workspace:write'). Alternatives are named (link_report for reader notes, resolve_note for the owner's resolution).

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