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

Annotations already declare readOnly=false, destructive=true, idempotent=true, openWorld=true, so the safety bar is lowered; the description still adds real context: the report-bucketing side effect of a timezone change, the manage-token auth requirement, partial-update semantics, and the underlying POST /sites/{site_id} call. It does not explain what aspect of this update is "destructive."

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?

Three dense sentences with no filler, front-loading what can be changed before the invocation hint, side effect, auth requirement and endpoint. The endpoint string is marginal but harmless.

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 partial-update tool with only one required field and no output schema, the description covers the mutation surface, the partial-send convention, the auth prerequisite and a key side effect. Conditional dependencies (share_password with sharing=private, multi_domain_option with multi_domain) are left entirely to the schema, which is acceptable at 100% 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 every parameter including share_password and multi_domain_option is already documented with format, enum and conditional requirements. The description's field list duplicates the schema rather than adding syntax or interaction detail, which is the baseline 3 case.

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+resource ("Change a site's") and enumerates the mutable attributes (name, sharing, timezone, multi-domain), which is well beyond a restatement of the title. It does not explicitly contrast with siblings like fathom_create_site or fathom_get_site, but the mutating scope is unmistakable.

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?

"Send only what changes" gives clear PATCH-style invocation guidance and "Needs a manage token for the site" states a prerequisite, which is more than nothing. However, no alternative tools are named and there is no explicit when-not (e.g., use fathom_get_site to inspect current values first).

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