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

Annotations only declare readOnlyHint=true, but the description carries substantial behavioral burden: the 100-by-row display cap vs the true filer count, the coverage.basis caveat, common-stock-only scope, off-cadence quarters, CUSIP resolution failures that can drop or mis-attribute rows, and the ~45-day EDGAR delay with tool_notes caveats. This is rich, non-obvious disclosure well beyond structured fields.

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?

The description is dense but nearly every clause earns its place: return shape, cap caveat, per-holder fields, coverage caveat, scope limits, sibling routing, and source cadence. The core purpose is front-loaded before the caveats. Slightly crowded, but the length is justified by the caveat burden for a data source with real attribution traps.

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?

No output schema exists, so the description must carry the return-value burden, and it does: it enumerates the top-level keys, the per-holder field list with units (value_usd in whole USD, pct_change vs prior quarter), the display-cap limitation, and the coverage.basis field to check before quoting aggregates. Nothing an agent needs to interpret the response 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?

The single ticker parameter is fully documented in the schema ('Stock ticker symbol (e.g. AAPL)'), and the description adds no syntax, constraint, or format detail beyond it. Baseline 3 applies when the schema already does the heavy lifting for a single 100%-covered 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?

States a specific verb+resource ('Which institutions hold one ticker, and which way they moved') and immediately enumerates the return shape. It distinguishes itself from siblings by explicitly labeling ol_ownership_changes as the 'direction-only view' and get_13f_holdings as the 'fund-keyed inverse', so an agent can place it precisely in the tool family.

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?

It names two alternatives with their distinguishing characteristics, which functions as routing guidance towards the correct sibling. However, it does not explicitly state the condition under which a caller should prefer this ticker-keyed view over them, leaving the 'when-to-use-this' inference to the agent.

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