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

Annotations only cover safety (readOnly, non-destructive, openWorld), so the description adds the operationally decisive facts: a reporting lag of up to 45 days, the fact that the latest visible quarter always trails real time, and that the data is a long-equity snapshot with no shorts/cash/options. It also explains position_change is computed against the same fund's prior quarter, which prevents misreading a field.

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-loads the definition, then usage triggers, then caveats, then field semantics — a sensible order with no wasted preamble. Slightly long, and enumerating the position_change values duplicates the enum in the schema, which is the only real redundancy.

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 an 11-parameter tool with no output schema and no required parameters, the description covers the domain, the temporal caveat, and the grain of each record well. Field-level return detail is thin — only position_change is characterized — so an agent still lacks a full picture of what columns come back, but nothing needed to invoke it correctly is missing.

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 100%, so the baseline is 3 and the schema already carries format details for cusip, quarter, cursor, and the enums. The description still adds real meaning beyond the schema by explaining what position_change values signify ('relative to the same fund's prior quarter') and why quarter choice is constrained by filing lag.

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?

States a specific verb and resource ('Returns 13F holdings — quarterly snapshots of equity positions held by institutional investment managers with $100M+ AUM') and defines the record grain as a (fund, security, quarter) tuple. The AUM threshold and 13F framing implicitly separate it from sibling datasets like get_fund_holdings (N-PORT mutual funds) and get_activist_stakes (13D/13G), so an agent can route without opening a schema.

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 an explicit trigger list: 'which institutions hold a stock, a fund's portfolio, position changes quarter-over-quarter, or whale activity in a specific name.' It also bounds the domain by listing what 13F excludes (shorts, cash, options, non-US equities), which steers the agent away from wrong questions. No sibling tool is named as an alternative for overlapping cases, so it stops short of full when-not guidance.

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