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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world), so the bar is lower, yet the description still adds real context: deterministic ordering (newest first), what each row contains, an explicit SIMULATED disclaimer on backtest figures, and the POLYRANK_API_KEY auth requirement. It does not discuss pagination or result caps, which is the only notable behavioral omission.

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?

Three compact sentences, each carrying distinct payload: what is returned, how the status filter behaves, then the auth and simulation caveats. The return shape is front-loaded and nothing is repeated from the schema or annotations.

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 read-only two-parameter list tool with no output schema, this covers nearly everything an agent needs: ownership scope, ordering, row contents, state vocabulary, auth, and the simulated-data warning. The only gap is the unaddressed `include_archived` flag and its relationship to the archived state.

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 description must carry the parameter meaning. It does decode the `status` enum values and clarify that only one state may be supplied, but `include_archived` is never mentioned at all, nor how it interacts with status=draft versus status=archived — leaving half of the two-parameter surface undocumented.

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 and scope: the caller's own saved strategies, returned newest first with state plus the latest backtest headline. It clearly implies a listing of user-owned strategies rather than a single lookup, which separates it from polyrank_get_strategy, but it never states that distinction explicitly or names any sibling.

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 only implied: an agent can infer this is the browse/overview call before drilling into polyrank_get_strategy or polyrank_list_backtests, but no when-to-use or when-not-to-use condition is spelled out. The one genuinely useful guidance sentence is that `status` accepts a single state only, which tells the agent not to attempt multi-state filtering.

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