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

Annotations already establish readOnly, openWorld, idempotent, and non-destructive behavior. The description adds meaningful behavioral context beyond those annotations: results are anonymized with no addresses, data comes from city open-data portals (Socrata), and unsupported jurisdictions return a specific flag (jurisdictionSupported=false). These details help the agent set expectations without contradicting the annotations.

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?

Three sentences pack the core function, output contents, data source, jurisdiction limitation, and use cases without redundancy. The most important scoping information ('~1500 ft', '24 months', 'Seattle') appears in the first sentence, which is ideal for quick agent parsing. No filler or repetition is present.

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?

Given the single parameter, rich output schema, and safety-laden annotations, the description covers everything an agent needs to invoke the tool correctly. It states the geographic scope, time window, output composition, data provenance, and the unsupported-jurisdiction fallback behavior. The only minor ambiguity — 'Seattle-area parcel' vs. schema's broader county coverage — is directly resolved by the description's own 'Currently supports Seattle' clause.

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?

The schema provides 100% description coverage for the single required 'address' parameter, including length constraints and a county-level description. The tool description adds the Seattle jurisdiction caveat but does not further elaborate parameter semantics beyond what the schema states. Per the baseline rule, this is a '3' — schema does the heavy lifting.

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 opens with a specific verb and resource: 'Aggregate permit activity within ~1500 ft of a Seattle-area parcel over the last 24 months.' It also enumerates the return contents (total count, category breakdown, anonymized recent permits), making the tool's scope unambiguous. The explicit focus on 'permit activity' distinguishes it from sibling tools like get_neighborhood_project_activity even without naming them.

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 description gives explicit use cases: 'Use to gauge neighborhood activity before quoting an unusual project, or to set homeowner expectations on what neighbors have built.' It also clarifies the jurisdictional constraint ('Currently supports Seattle; other jurisdictions return jurisdictionSupported=false'), which tells the agent when the tool is applicable. It stops short of naming alternative tools or stating when not to use it, so it is not a full 5.

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