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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds the crucial mechanism beyond that: companyIds replaces the whole list rather than appending, so omitted brands are unfollowed. It also notes the downstream effect on the home view and offer calendar. It doesn't cover error behavior for invalid/unknown ids or workspace scoping, keeping it below a 5.

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, front-loaded with purpose and then the destructive caveat, with zero filler. The replacement warning is placed before the agent could plausibly act on the tool.

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 destructive mutation with no output schema, the description plus annotations give the agent enough to act safely: replacement semantics, a required read-first step, and the user-visible consequence. Missing only return shape and failure modes, which is acceptable given annotation coverage.

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 all three parameters are documented, but the description still adds value by explaining the replace-vs-append semantics of companyIds and the safe procedure for building that list. It says nothing about projectId/workspaceId, which the schema carries on its own.

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: 'Set the brands the user follows in Sightglass.' It is immediately distinguishable from sightglass_list_saved (read) and other sibling tools, and the follow-up sentence clarifies the replacement semantics of the call.

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?

Explicitly directs the agent to read the current state with sightglass_list_saved (kind=following) before calling and to include brands to keep, which is exactly the procedural guidance needed for a replace-style tool. It lacks explicit when-not/exclusion conditions, but the destructive mechanics are clear.

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