Sessions to watch

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

Annotations already signal a safe read (readOnlyHint=true), and the description adds real behavior: 20 items per page, deterministic ordering by start date then id, and the fact that total spans all pages rather than the current page. It does not describe what an individual session record contains or what happens at the range boundary, but the output schema can carry that. Solid incremental value, not rich.

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 sentences, zero filler, and the identity of the tool (which sessions) is front-loaded before the pagination contract. The middle clause packing ordering and page size is dense but readable. Slight awkwardness in the trailing pagination sentence keeps it from a 5.

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 an output schema present, the description need not enumerate return fields, and it correctly spends its words on the two return values whose semantics are non-obvious (total across pages, next_cursor as continuation token). Combined with the explicit date-range filter and page size, an agent has enough to call this correctly on the first try.

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 schema already explains cursor, from_date and to_date, including the 92-day cap. The description restates the range boundaries in prose but adds no format, constraint or edge-case detail the schema lacks. Baseline 3 is the correct ceiling here.

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 pairs a specific verb ("List") with a precise resource and a compound filter: sessions that are PLANNED or OPEN, start within the given date range, and are less than half full. That is far more informative than the title alone. It stops short of naming a sibling, so an agent must still infer how this differs from sessions_in_week or session_detail.

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?

Usage guidance is limited to pagination mechanics: call again with next_cursor when it is present. There is no statement of when to reach for this tool rather than a neighbouring session-listing tool, nor any prerequisite or exclusion. The selection criteria are implied by the filter definition (unfilled upcoming sessions), which is helpful but left implicit.

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