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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful semantics on top: an unmeasured axis is a first-class answer, published deliberately so the gap is visible, never an error and never a zero — and explicitly not a certification. That is exactly the kind of interpretive context annotations cannot carry.

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?

The resource identity is front-loaded, which is good, but the opening is one long comma-spliced sentence enumerating returned fields, and the disclaimer tail ('never an error and never a zero. Never a certification.') is fragmented. Every clause earns its place, but the structure could be considerably tighter.

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?

An output schema exists, yet the description still spends most of its length listing return fields rather than explains when to pick this axis over its siblings or what the affect axis is for. The interpretive rule about unmeasured rows is valuable, but routing information is entirely absent for a tool embedded in a 40-tool family.

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?

Zero parameters, so the baseline is 4. The description reinforces this by stating the tool 'takes no argument', which prevents any attempt to pass a filter or axis id, though it could have added a word about how to target a specific run or date.

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 precisely ("the affect axis of the live GSPC board") and distinguishes it from the many axis_* siblings by which axis it is. But it never explains what the 'affect' axis measures, so an agent can tell which tool this is, not what concept it represents or how it relates to get_axis / get_card.

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?

There is no statement of when to call this versus get_axis, get_card, board_totals, or the forty-odd other axis_* tools. The only selection cue is the axis name itself, which an agent must already understand to choose correctly.

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