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 covered. The description adds genuine context beyond that: the comparison is predicted net versus net realised from *settled* funding over the hold, which tells the agent the numbers are historical and settlement-based rather than projected. It does not disclose the evaluation window, sample size, or caching/refresh behaviour.

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 front-loaded sentence that names the subject first and then lists the returned metrics, with no filler. It is dense and slightly jargon-heavy ('predicted net vs net realised from settled funding over the hold'), but every clause carries information.

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?

With no output schema and no parameters, the description carries the full burden of explaining what comes back, and it does list the metric families. However, it omits the time window covered, how many picks are included, and whether results are aggregated or per-pick, which an agent needs to interpret or cite the output correctly.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. The description correctly implies no input is needed to retrieve the record.

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 states a specific resource — the realised performance record of AfterFees' daily top picks — and enumerates the metrics returned (predicted vs realised net, hit rate, mean error, latest picks). It is clearly a read-only reporting tool, but it does not name or contrast any sibling such as best_opportunities or my_positions, so the agent must infer the boundary.

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 deduce this is the place to verify past pick accuracy rather than to find new opportunities. There is no explicit when-to-use statement, no exclusion, and no pointer to best_opportunities for current picks, which is the obvious alternative an agent would weigh.

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