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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: each result carries the client association, the agency's assignment, and the connected services (e.g. Cloudflare zone), plus a pointer to which tools to use for those services.

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 with the scope and return shape front-loaded and no filler. The second sentence is a dense run-on involving the service/Cloudflare routing idea, costing a little readability.

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?

Return contents are described, filtering is delegated to a well-documented nested schema, and no output schema exists to lean on, so the description carries its share. What's missing is a note on result volume or pagination behavior for a fleet-wide enumeration.

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?

The description only says results are 'optionally filtered' without naming or explaining any filter field. The nested schema does document each filter (tags, status, tag_match, plugin_slug, selection_id) so the baseline of 3 applies, and the description adds nothing on top of it.

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 ('Enumerate connected sites') and scopes it to 'the current agency', which is real information an agent can't get from the name alone. It does not explicitly distinguish itself from close siblings like fleet__list_site_groups or recipe__fleet_inventory, so it stops short of a 5.

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?

Usage is only implied: 'optionally filtered' suggests using it as a listing step before acting on a site. There is a useful routing hint ('use that service's tools for the site'), but no explicit when/when-not versus list_site_groups or fleet_inventory.

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