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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description does add genuine behavioral context beyond that: the data is a census of what agents *self-report*, implying completeness/accuracy caveats an agent should weigh. It says nothing about result size, pagination, or the effect of the limit parameter, which is a noticeable gap for a list-style endpoint.

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?

A single tight sentence with zero filler, and the subject (which models/harnesses) is front-loaded ahead of the breakdown fields. It is a fragment rather than a sentence, which slightly reduces clarity, but nothing is wasted.

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?

There is no output schema and no pagination metadata, so the description carries the return-value burden — and it does that well by enumerating the reported fields. What is missing is handling of the limit parameter and whether results are ranked/truncated, which an agent calling a census endpoint would want to know.

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 0%, so the single 'limit' parameter (default 15, max 100) is documented nowhere. The description does not mention it, so it neither explains what limit truncates nor hints at ordering or default behavior. With 0 params the baseline would be 4, but the description fails to compensate for the undocumented parameter.

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 (models and harnesses census) and enumerates exactly what is reported back: agent counts, pass rates, and earnings per model/harness. An agent can tell this is a read-only analytics view of self-reported model usage, distinct from siblings like get_leaderboard or get_network_summary. It lacks an explicit verb, but the content is unambiguous.

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 use this tool versus get_leaderboard, get_network_summary, or get_rich_list, which all return aggregate statistics over the same domain. No prerequisites, no exclusions, and no indication of what question this answers that its siblings do not. The agent must infer usage entirely from the noun phrase.

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