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

Annotations only declare readOnlyHint and openWorldHint=false, so the description carries most of the behavioral load. It adds genuine context beyond annotations: the data's vintage is a weekly cutoff, flows cover a three-month window, results are aggregate totals only, and per-fund detail is apparently gated ('not free'). It stops short of stating auth, rate limits, or return format.

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?

It is a single sentence with no filler, which is efficient, but it is a dense run-on with a semicolon and a cryptic trailing parenthetical. The most decision-relevant fact (totals only, no per-fund detail) is buried at the end rather than front-loaded.

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, so the description effectively doubles as the return-value spec, and it does list the four categories of data returned. For a zero-parameter read-only summary tool this is close to sufficient; only the exact shape and units of the returned aggregates are left unstated.

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 clarify and the baseline of 4 applies. The schema is an empty object with no fields to misinterpret.

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 enumerates the data points returned (data vintage week, fund counts by category, best YTD return, three-month net flows), so an agent can infer this is an aggregate market-statistics tool. However, it never states a verb or names the resource in a clean phrase — it opens with the fragment 'The week the data runs to' — so the purpose has to be decoded from a list rather than read. It only weakly separates itself from siblings like get_mutual_funds or get_mutual_fund_league_table.

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?

The parenthetical 'totals only, as on the front page; which funds is not free' implies this is a summary-level tool and that per-fund breakdowns live elsewhere, which is an implied usage boundary. But no sibling is named and there is no explicit 'use this when...' statement, leaving the agent to guess which of the several fund/pension siblings to pick.

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