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

The annotations declare destructiveHint=true and idempotentHint=true, and the description complements that by explaining the merge semantics: fields are merged, null deletes its key, events merges per entry. It also exposes the destructive behavior of retention_days (shortening schedules permanent deletion at the nightly prune, confirm with owner first). This is meaningful behavioral context beyond the hints.

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?

The entire description is two dense sentences with no filler. The first sentence front-loads the core behavior (merge, null-deletes, events-per-entry), and the second sentence clarifies the one exception (name/domain update the site record). Every clause earns its place.

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?

Given 10 params, 100% schema coverage, an output schema, and annotations, the description caps the missing context: merge semantics, null-delete behavior, and the destructive retention_days caveat. An agent can invoke it correctly without needing more prose; the structured fields carry the rest.

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 each parameter already has a description; the tool description adds the crucial merge/delete semantics and explicitly calls out name/domain as record-level fields. The description doesn't repeat every parameter, which is appropriate, but the merge semantic is essential and is stated. Slight deduction because the description could have summarized the event/funnel shapes slightly more, though the schema already covers them.

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 opens with a clear verb+resource ('Save or amend what a site is for') and immediately distinguishes the tool's merge behavior from a plain overwrite. It also explains that name/domain update the site record itself, which separates it from the context-field behavior and from siblings like create_site or get_site_context.

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?

The description and the site parameter anchor the tool to an existing site ('the site's data-site code, from its script tag or list_sites'), and the schema adds explicit guidance about omitting site for single-site accounts and reading the code from the script tag in a tracked project. It doesn't explicitly say 'use get_site_context to read before updating' but the merge semantics imply an existing context.

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