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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the agent knows this is a non-destructive, repeatable write. The description adds the upsert framing, which is useful, but says nothing about permission requirements, behavior on an invalid siteId, or side effects on the primary-site flag. With annotations carrying the safety profile, this is adequate but not rich.

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 short sentences: the capability and field list come first, the upsert selector and related tools follow. Every clause carries information; nothing is padded.

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?

With an output schema present, return values need not be described, and the 5 parameters are fully covered by the schema. The description covers the add/edit distinction and field scope, leaving only edge-case behavior (invalid siteId, effect of promoting a new primary) unstated.

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 description coverage is 100%, so every parameter (including the nested capture object) is already documented in the schema. The description restates siteId's edit semantics and loosely renames 'domain' as 'hostname', adding no syntax or format detail beyond the schema. Baseline 3 applies.

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 states a specific verb pair (adds or edits) and resource (a website), then enumerates the manageable fields (hostname, name, primary, lead-capture). It does not spell out how it differs from near-neighbours like update_asset or update_brand_profile, offering only a 'Related:' pointer list, so sibling differentiation is partial.

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?

'Pass siteId to edit' explicitly tells the agent which branch of the upsert it is invoking, matching the schema's 'Omit to add'. The Related list routes the agent to list_sites for discovery and delete_site for removal, but there are no stated exclusions or prerequisites (e.g. what happens with an unknown siteId).

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