district_summary

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

With no annotations, the description still carries the key context: the data source (BoardStat/BetaNYC, NYC Open Data, 2020 on), the warning that it is not an official City report, and the crucial interpretive caveats that 311 counts are reports rather than problems and that 'closed' is not 'fixed'. It omits other behavioral traits such as cost/latency, how the limit interacts with the listed top problems, or failure modes for dates outside the 2020-on window.

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-loaded with the deliverable (totals for district and period) followed by the enumerated metrics, then provenance and interpretation caveats. The caveats are dense and semicolon-packed but each one prevents a real misreading, so little could be cut without losing information.

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 seven-parameter aggregation tool with no output schema, the description adequately explains what comes back (counts, open counts, duration stats, top problems with comparison shares) and qualifies the data's provenance and semantics. The main gap is that the 'limit' parameter's meaning — which rows it caps — is never clarified, and the 2020-on data boundary isn't tied to the period parameters.

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, and the description adds real meaning by stating that a single district (community or council) and a single period scope the totals, reinforcing the mutual-exclusion constraint documented in the schema. It adds no syntax detail for date forms or fiscal_year beyond what the schema already provides.

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?

Names a concrete verb (totals) and resource (community or council district for a period) and enumerates the metrics returned: request counts, not-yet-closed counts, median/average days to close, top problems, and each problem's share versus borough and city. That metric list clearly separates it from sibling tools like top_problems or still_open, which do not compute borough/city comparison shares.

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 scope (one district, one period) implies when to use it for aggregate roll-ups, but the description never explicitly names an alternative or a when-not condition, leaving the agent to infer the choice against siblings such as problem_trend, find_requests, or top_problems. The only explicit constraints (council vs community district mutual exclusion, date forms) live in the schema, not the description.

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