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

Annotations already mark destructiveHint=true. The description adds important behavioral detail: the filter replacement semantics and the instruction to send the whole filter state back. This goes beyond annotation coverage and helps the agent avoid data loss.

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 sentences, no fluff. The first sentence lists actions, the second immediately gives a critical usage caveat. Perfectly front-loaded and every word is informative.

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?

The description covers the key complexity (filter replacement), the prerequisite (list_views), and the need to send full state. The detailed filter schema handles parameter specifics. Minor omissions like error handling are not essential for a destructive update tool with no output schema.

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 only 33%, but the description ties each main parameter to its purpose (rename→name, layout→layout, grouping→groupBy, share→shared, replace filter→filter). The detailed filter schema complements the description, making parameter meaning clear.

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?

The description clearly states the tool updates a saved view and enumerates specific actions: rename, change layout/grouping, share, or replace the filter. This distinguishes it from siblings like create_view, delete_view, and list_views.

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?

Provides explicit prerequisite: 'Read the view first with list_views' and explains the critical behavior that a filter replaces the stored one rather than merging. This guides correct invocation, though it does not explicitly state when to use alternatives like create_view.

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