list_analytics

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds real behavior beyond them: posts are returned 'most recent first', insights are read-only and plan-gated, and include_extras data 'stays off until snapshot extras are switched on, and this does not start a new sync'. Those last points are the kind of side-effect clarity annotations cannot express. It omits failure behavior for invalid accounts or empty date ranges.

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?

It is a single dense paragraph where nearly every clause carries information (view semantics, platform exception, plan gate, presentation mapping). It would scan faster with the three view modes split into distinct sentences or lines, and the long platform enumeration adds little an agent needs.

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 10-parameter, three-mode, no-output-schema tool, the description covers the mode split, platform caveat, pagination ordering, plan gating, presentation formats, and the include_extras sync caveat. The main remaining gap is that date-range defaults and their interaction with view=insights are left entirely to the schema.

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?

With schema coverage at 100%, baseline is 3; the description earns more by giving presentation values actual meaning ('compact for Telegram/mobile, table for Markdown clients, json for custom chart/card renderers') and by explaining what include_extras surfaces and that it is inert until extras are enabled. Checkpoint values and account-scoping rules are also restated with context, though from/to and limit/offset add nothing 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?

The description names the resource (analytics for connected social accounts) and enumerates exactly what each of the three views returns, so an agent can tell this apart from list_posts or list_comments. It never states an explicit action verb such as 'retrieve' or 'list', relying on the surface-noun phrase 'Analytics for...' plus the per-view return lists to imply read retrieval.

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?

It routes between the three view modes with concrete conditions: per-post data goes to view=posts, while 'Google Business has no per-post rows; its totals are on view=accounts' is an explicit when-not rule. It also gates view=insights behind 'Pro plan or higher'. It does not point to sibling tools for adjacent needs (post content, comments, account discovery beyond the parenthetical 'from list_accounts').

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