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

Even though annotations already say readOnlyHint and openWorldHint, the description adds substantial behavioral context: it is a founder preview pending licensing, it returns schema/row-count/capped sample, it never returns raw geometry, it privacy-screens person-like fields and Survey123 layers and reports refusals, and the screen can be conservative. This far exceeds the annotation bar and gives an agent accurate expectations for call outcomes.

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 long and somewhat repetitive ('FOUNDER PREVIEW, NOT A PUBLISHED FEED' and later 'it is served here for founder evaluation only'). However, it is well-structured with explicit 'HOW TO USE IT' and 'WHAT IT WILL NOT DO' sections, and it front-loads the purpose. Some sentences could be tightened without losing information, so it earns a 3.

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 tool with no output schema, the description covers the necessary context: what the search returns, what reading a layer returns, the geometry restriction, privacy filter behavior, refusal reporting, and licensing limitations. It does not mention rate limits or timeouts, but for its complexity it is close to 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?

With 100% schema description coverage, the baseline is 3. The description goes beyond the schema by explaining the two-phase workflow (search returns item_id; item_id must be paired with the same source), describing what `filter` matches across text fields, and noting that `source` defaults to longbeach. It adds real semantic value that the schema alone does not convey.

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-resource pair: 'Search and read a city GIS, a public ArcGIS organization of map layers,' and enumerates coverage (parcels, zoning, districts, bikeways, parks, neighborhoods, permits). This clearly sets it apart from the sibling tools like city_calendar or events_list. It does not explicitly name a sibling or contrast with city_datasets/city_records, which would be needed for a 5, but the GIS focus is unmistakable.

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 workflow guidance: first call with `search` to get item ids, then call with `item_id` and the same `source` to read a layer. It also explains the default source and when to pass `source`. However, it never tells the agent when to prefer this tool over a sibling like city_datasets or city_records, so it lacks explicit exclusions/alternatives.

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