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

Annotations only declare readOnlyHint and openWorldHint; the description goes further by disclosing the provenance ('read from the agency's dataset'), the refresh cadence ('refreshed daily'), and the aggregate nature of the output ('how many are on each list, by ZIP and status'), plus a free/paid framing. It stops short of describing pagination, volume limits, or return structure, which keeps it below a 5.

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 resource definition is front-loaded and the domain enumeration is dense but informative. The 'Free:' marketing framing and the audience sentence are slightly promotional yet short, so there is little genuine waste.

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, single-optional-parameter tool with no output schema, the description covers source, freshness, what the numbers represent, and the audience restriction. The main residual ambiguity is whether the call returns the catalog of lists or per-building records, though 'leave out to see every list' in the schema largely resolves that.

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?

With one optional parameter and 100% schema description coverage, the schema already explains the 'list' id and even supplies an example (sb721-cited). The description adds only indirect meaning via 'how many are on each list, by ZIP and status', which hints at the aggregation dimension but not the id format or valid values.

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 gives a concrete resource ('buildings and facilities that owe a legally required inspection, filing or fix') and enumerates the domains covered (SB 721 balconies, LA benchmarking, code cases, retrofits, stormwater permits), so the agent knows exactly what data is behind the tool. It does not name a sibling tool to differentiate from, but the enumerated scope is distinctive enough that confusion with list_compliance_watches or get_compliance_items is limited.

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 states the audience ('for the firms that do this work') and one exclusionary rule ('not for finding or profiling people'), which is a useful boundary. However, it gives no guidance on when to pick this over the closely named siblings get_compliance_items, get_compliance_changes, or list_compliance_watches, so the choice is left implicit.

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