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

Goes well beyond annotations: the destructive hint is contextualized ("revision history keeps the old copy"), cost is quantified ("1 per 20 strings" of AI credits), required scopes are stated (demos:read, demos:write), and subtle behaviors are disclosed — {{variables}} are preserved, auto-stitched navigation links are untouched unless named, and then only rewritten once per link group.

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 and example instruction, then progressively narrower scoping rules. Dense — a long paragraph with nested parentheticals and brace notation — but nearly every clause carries operative information, so little is wasted.

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 7-parameter destructive mutation with no output schema, this covers cost, permissions, reversibility and scoping thoroughly. The remaining gap is the return shape when `apply=false` (what a "suggestion" contains and whether it maps to stepIds), which an agent would want before running in review mode.

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 already 86%, yet the description still adds meaning: a concrete `instruction` example ("for a CFO audience, shorter, mention month-end close"), the `apply` default-true behavior with what false yields, and the non-obvious `stepIds` semantics for stitched link groups. It also clarifies `fields` intent for choices ("a card with choices has no button").

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 ("Rewrites a demo's copy with AtriumKit's AI") and anchors it to a known in-product feature ("the same strings as 'Write with AI' in the editor"). It doesn't name the closest sibling (replace_in_copy) to draw the AI-rewrite vs literal-replacement boundary explicitly, so differentiation is inferable rather than stated.

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 usage context: it covers all steps or hotspots by default, or can be narrowed via `stepIds`/`fields`, and it explains the two operating modes (apply=true saves, apply=false returns suggestions to review). No explicit when-not or named alternative, so it stops short of a 5.

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