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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the safety profile is done. The description adds genuinely non-structured behavior: missing measurements are published as declared gaps rather than errors or zeros, and the output is explicitly not a certification. That pre-empts two plausible agent misinterpretations. It stops short of saying whether rows are paginated or how staleness is signalled.

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?

Front-loaded with the identity of the axis, then the no-argument fact, then the field inventory, then the two interpretive caveats. Every sentence carries content and nothing repeats the schema. The field enumeration is dense but scannable; the final two-sentence caveat block is slightly long relative to the first.

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 zero-argument, read-only tool with an output schema and full annotation coverage, this is close to complete: the agent knows what the axis is, that it needs no input, what a row contains, and how to treat missing data. The one thing left unstated is the relationship to the aggregate and retrieval siblings (board_totals, get_axis), which would help an agent sequence calls.

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, which sets a baseline of 4, and the description reinforces it by stating outright that the tool takes no argument. The field list it gives is about the returned row, not inputs, so it neither helps nor hurts input semantics. No gap to compensate for.

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?

Names a specific resource: the company-practice axis of the live GSPC board, and enumerates the fields the row carries (n, accuracy, interval, status, family, kind, source URL, dates). Against ~35 sibling axis_* tools, the qualifier 'company-practice' is what distinguishes it, and 'this tool IS the axis, so it takes no argument' removes ambiguity about scope. It does not explicitly contrast with get_axis or board_totals, which keeps it short of a 5.

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?

No explicit statement of when to choose this over get_axis, board_totals, or the other axis_* siblings; the name is the only routing signal. What it does supply is interpretive guidance: an unmeasured axis is a first-class answer, not an error and not a zero, which tells the agent how to read the result. That is usage-adjacent, but it never names an alternative or a condition for exclusion.

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