get_statistics

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description reinforces read-only status and adds behavioral detail not in annotations: 'Returns buckets sorted by count descending plus the total.' This gives an agent a clear expectation of the response shape and ordering, exceeding the minimum disclosure.

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 three tight sentences, front-loads the core purpose, and uses a code block for the enum list. Every sentence contributes distinct information: the action, the grouping options, the filtering behavior, and the output format. No filler or 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 a read-only aggregator with 9 optional parameters, an output schema, and rich annotations, the description covers the main functional behavior, grouping, filtering, and return tallies. It does not explicitly mention pagination or empty-result behavior, but the output schema and read-only annotations cover most agent needs. A small gap is the lack of differentiation from the sibling count_filings, but overall it is sufficiently complete.

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. The description lists group_by values (redundant with the schema enum) and states that filters narrow the population, but it adds no per-parameter meaning beyond the schema. It does not need to compensate for a coverage gap, so a 3 is appropriate.

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 states a specific verb and resource: 'count filings grouped by one dimension.' It enumerates allowable group_by values and clarifies the output (buckets plus total), making the tool's purpose distinct from siblings like count_filings, which presumably returns a simple total. The tool's role is unambiguous.

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 lead-in 'Use this to' provides a use case, and 'Optional filters narrow the population' gives general context. However, it does not explicitly differentiate get_statistics from sibling count_filings or state when to prefer one over the other, leaving the choice to inference rather than explicit guidance.

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