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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered, but the description adds non-obvious behavior the schema cannot express: multi-site or unfiltered queries return deliberately limited per-site data, and full configuration requires a separate single-SiteId call. That payload-shape pitfall is exactly the kind of behavioral context an agent needs to avoid a wrong conclusion from the response.

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 front-loaded purpose and the two bullet rules are efficient, but the important-behavior section repeats the same point three times ("expected behavior", "reduce payload size", "we recommend retrieving the list of site IDs first"), and the Mindbody call count plus endpoint path add little for an agent. Roughly a third of the text is restatement.

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 read-only, six-parameter, non-nested tool with no output schema, the description covers the dominant risk (partial data on multi-site queries) and the calling pattern thoroughly. Minor gaps remain around pagination defaults and the two include* flags, which the schema does label but the description never contextualizes.

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 the baseline is 3, and the description goes beyond it by explaining the semantic difference between the siteIds array being omitted, containing one element, or containing many. It does not explain includeLeadChannels, includePerStaffPricing, the siteId header default of -99, or limit/offset paging, so it stops short of full coverage.

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 ("Gets a list of sites") plus the access scope ("sites that the developer has permission to view"), and names the concrete endpoint GET /site/sites. An agent can distinguish this from siblings like get_locations or connect_studio without opening any schema.

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?

Gives explicit branching rules: no SiteIds returns all accessible sites, one SiteIds returns detailed info for that site, and it recommends retrieving the ID list first then querying each site individually when full detail is required. That is a concrete when-to-use and how-to-sequence instruction rather than implied usage.

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