get_custom_items

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

Annotations already declare readOnly=true and openWorld=false, so 'read-only' is redundant. The valuable addition is the disclosed side effect: the call 'refreshes the cached definitions the other tools use to label custom fields' – a non-obvious behavioral trait an agent would not infer from the schema or annotations.

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?

Front-loaded with the primary purpose, followed by the returned-field list and the detail-tool pointer. Two short paragraphs, no filler. The loose '...' enumeration costs a little precision but not much length.

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 no-output-schema list tool with safety already covered by annotations, the description states the returned fields, discloses the cache-refresh side effect, and points to the detail sibling. An agent has enough to call it correctly; only the absence of any pagination/scope note keeps it from 5.

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?

Only one parameter (athlete_id) and schema description coverage is 100% ('Default: the configured athlete'), so the schema carries the semantics. The description adds nothing about the parameter, making the baseline 3 correct.

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 ('list the athlete's custom items'), enumerates the item categories (charts, activity, interval and wellness fields, streams, zones) and the returned fields (id, name, type, description). It also names the sibling get_custom_item_by_id for the single-item case, so the agent can distinguish the two without opening schemas.

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?

'Use to list...' gives a clear triggering context, and the closing pointer 'Full definition of one item: get_custom_item_by_id' routes the agent to the right alternative when a single item is needed. It stops short of an explicit when-not, so it lands at 4 rather than 5.

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