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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: a named UNREACHABLE failure state and the guarantee that no cached number is presented as live, plus the epistemic caveat 'we measure, never certify'. It stops short of auth, rate-limit or freshness-bound information.

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 purpose and source URL, then the return contract, then the detail mode, then the failure state — a sensible order. Some rhetorical redundancy ('never summed and never swapped', 'we measure, never certify') pads an otherwise tight paragraph, but every clause carries domain meaning.

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 return values need no further explanation, and the description still characterizes the shape and the failure mode. For a zero-required-parameter read tool with full annotation coverage, the remaining gap is minor — no mention of caching TTL beyond the live claim, or of what an agent should do after an UNREACHABLE response.

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 coverage is 100% and the single enum parameter is already fully documented in the schema, including what each mode returns. The description restates the same summary/full split without adding syntax or defaults beyond the schema, so the baseline of 3 applies.

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 (live GSPC board totals from councilof.ai/api/gspc) and enumerates exactly what comes back: slot count, measured count with their kind, the separation line, and as_of dates. The slot-vs-measurement distinction is defined inline, so an agent knows what 'count' means here, which no sibling tool (axis_*, get_card, measurement_index) provides.

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?

Gives clear guidance on the detail switch ('compact by default; pass detail "full" for...'), which is the only choice the caller makes. It never says when to reach for this rather than measurement_index or get_card, nor states any preconditions, so routing between siblings is left to inference.

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