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

Annotations declare destructiveHint=true and readOnlyHint=false; the description adds genuinely new behavioral context by stating that artifact_id, the underlying brain object, and share links survive the update — important reassurance for a destructive-flagged mutation. It does not discuss permissions, reversibility, or what happens to state keys not passed.

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?

Two tight sentences, front-loaded with the action and field list, followed by the partial-update rule and the identity guarantee. No filler.

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?

Covers the mutation semantics and identity preservation for a destructive tool with no output schema, which is the key information an agent needs. Minor gap: no statement on how state keys interact with a whole-view source replacement when both are supplied.

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?

With 80% schema coverage the schema already documents artifact_id, source, and spec_version, but the description adds the non-obvious contract that only changed fields need be sent (patch-style semantics) and that identity fields are preserved. It does not clarify whether 'state' merges or replaces.

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 ('Change a saved view in place') and enumerates the mutable fields (source, title, spec_version, state). It is clearly distinguishable from a creation tool, though it never names generate_view/show_view to route the agent explicitly.

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?

'Change a saved view in place' plus 'Pass only what changes' gives clear context that this is a partial-update operation on an existing artifact rather than a new view. No explicit when-not or named alternative is provided, so it stops short of full routing guidance.

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