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

The readOnlyHint/idempotentHint/destructiveHint annotations already establish the safety profile, so the description only needs incremental context. It does add that the catalog reflects sources scanned daily, but says nothing about result ordering, volume, or whether the returned 'kind' labels are the canonical values used by other tools.

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 tight sentences with no filler; the resource definition comes first and the filtering capability second. The only structural weakness is that the opening is a fragment without a verb, so the action has to be inferred from the title.

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 two-optional-parameter read-only list tool this is close to sufficient, but there is no output schema, so the description is the only place to say what a result row contains (name, kind, URL?). That matters because 'kind' is described as 'exact kind label as returned in results' – the shape of those results is never characterized.

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 both parameters are already fully documented, including the exact-kind requirement and the example labels. The description only restates that 'q' matches name or topic and 'kind' is a filter, adding no meaning beyond the schema – baseline 3 applies.

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 enumerates exactly what a 'source' is (public calendars, Meetup groups, Luma pages, conferences, venues, company event pages) and says the bot scans them daily, which clearly separates this catalog-listing tool from the meetup-event siblings. It falls short of a 5 only because the verb is implicit – the text is a noun phrase relying on the title 'List sources' to convey that it returns a list.

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?

Filtering guidance is stated ('filter by kind or free text (name or topic)'), which implies the tool is for browsing/discovering the source catalog. However, there is no explicit when-to-use versus get_meetup, search_meetups, or list_topics, and no hint that this is the place to obtain valid 'kind' labels before calling the meetup tools – a natural and valuable routing cue that is omitted.

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