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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds real behavioral context: newest-first ordering and the nature of the returned content ('personalized text, which may describe next actions'), which helps an agent decide whether the result is worth reading.

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 short sentences with no waste; ordering and pagination guidance are front-loaded. The clause 'which may describe next actions' is slightly hedged but still informative about payload character.

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?

With 0 required params, full schema coverage, and annotations covering safety, the remaining burden is describing what comes back — the description does this (personalized text, next actions) and explains pagination. Minor gap: no signal on total volume or how to know when paging is exhausted.

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 limit and offset are already fully documented in the schema, making 3 the baseline. The description reinforces offset's pagination role ('page through older meetings') but adds no format, boundary, or default detail beyond the schema.

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 ('List') and resource ('Referna meeting recaps') with scope ('the key owner's') and ordering ('newest first'). It does not explicitly contrast itself with the sibling get_meeting_recap, but the plural/list framing makes the distinction inferable.

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 offset to page through older meetings' gives a usage hint for pagination, which is genuinely actionable. However, there is no statement of when to use this tool versus get_meeting_recap, and no preconditions or exclusions are given — usage is implied rather than specified.

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