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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is semantic context — and it delivers: no arguments are taken, an UNMEASURED axis is a declared gap rather than an error or a zero, and the output is never a certification. These are non-obvious behavioural facts an agent could not infer from the schema. It stops short of noting the canonical board URL's freshness or access characteristics.

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?

One front-loaded sentence establishes identity and the no-argument constraint, followed by the payload list and two short caveats. Nothing is padded, but the middle field list is dense and jargon-heavy, and the trailing fragment 'Never a certification.' would read better attached to the preceding caveat.

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, so the tool needn't explain return values — yet it lists field names without defining them (what 'n', 'accuracy', 'interval', 'family', 'kind' mean or how they relate). Given a zero-argument tool whose only real failure mode is misselection among dozens of sibling axes, the absence of any disambiguation leaves a genuine gap.

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 explicitly saying the tool takes no argument, pre-empting an agent from inventing or hunting for parameters. The field list it provides actually describes the return payload, not inputs, so it adds no real parameter meaning beyond the empty 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 a specific resource (the humanoid-labour-index axis of the live GSPC board) and enumerates exactly what a row contains (n, accuracy, interval, MEASURED/UNMEASURED status, family, kind, bank or run-artifact URL, dates). That is far more than a restatement of the title. However, with ~34 sibling axis_* tools including near-neighbours like axis_labour-components and axis_humanoid-deployment, it offers no differentiation from them.

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 is implied rather than stated: read this tool to obtain the humanoid-labour-index row. There is no explicit guidance on when to prefer it over get_axis, measurement_index, board_totals, or the closely related labour/humanoid axis siblings. The clarification that an unmeasured result is a legitimate answer does usefully shape interpretation, but not selection.

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