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

Annotations already cover readOnly/idempotent/non-destructive, and the description still adds substantial behavioral context beyond them: split/bonus share adjustment via meta.share_adjustment, multi-quarter span detection via meta.gap_quarters, and the crucial coverage caveat that public 'exit' can mean dropping below the 1% naming threshold (listed_from/listed_to). This is exactly the kind of interpretation-critical detail annotations cannot carry.

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?

Dense but front-loaded: purpose first, then semantics, then coverage caveat. Every sentence carries information, though the parenthetical meta-field references make it heavy for a single paragraph; slightly more structural separation would help scanning.

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, yet the description documents the relevant return structures (per-holder statuses, share/% deltas, renames, reclassifications, meta.share_adjustment, meta.gap_quarters, summary). An agent has enough to call it and interpret results without opening follow-up tools.

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 coverage is 100% so the baseline is 3, but the description adds real meaning: it restates the `from` default behavior and ties parameters to output signals (gap_quarters, listed_from/listed_to) that the schema does not connect. The aliasing of symbol/ticker/identifier is left to the schema, which handles it adequately.

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?

Opens with a specific verb+resource+scope: 'Quarter-over-quarter diff of a stock's named shareholders', and enumerates the exact statuses (entry, exit, increased, reduced, unchanged) plus deltas. This clearly separates it from sibling readers like get_named_holders (snapshot) and get_named_holder_history (time series).

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 gives useful operating context (from defaults to the prior quarter, gap_quarters signals a multi-quarter span), but it never names when to choose this over get_named_holders or get_named_holder_history. Usage is implied by the diff framing rather than explicitly routed.

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