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

With annotations covering safety (readOnly, idempotent, non-destructive, openWorld), the description adds substantive behavior beyond them: id resolution, endpoint-observation requirements, ranking mechanics, and returned provenance/source-line references. It also discloses the key caveat that pre-2011 benchmark-break comparisons are published estimates, not beneficial-owner flows.

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 core question, then adds constraints, output shape, and caveats in dense but well-ordered sentences. Every sentence carries domain information, though the return-value enumeration in sentence three is long and could be trimmed.

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, and the description compensates by enumerating the return payload (endpoint values, absolute/percent change, source line references, provenance, custodial/methodology caveats). Combined with id-resolution and endpoint requirements, an agent has everything needed to call and interpret the tool.

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%, with minItems/maxItems, the YYYY-MM pattern, and enum for response_format all already documented. The description's mention of 'two to eight holders' and 'two exact months' merely restates those constraints rather than adding syntax or format meaning, so the baseline 3 applies.

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 precise verb and resource – comparing Treasury holdings changes across two to eight MFH holders between two exact months – and specifies the ranking basis (absolute USD-million change). An agent can distinguish this from siblings like treasury_tic_rank_holders or treasury_tic_holder_history 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 clear preconditions for use: two-to-eight holders, two exact months, and the requirement that primary observations exist at both endpoints. It never names the adjacent sibling tools (find_holders, rank_holders, holder_history) or states when to prefer them, so no explicit alternative routing exists.

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