searchSearch PermitReporter reviewed guidance and privacy-minimized collected building-permit records. Returns canonical URLs for citation. Call fetch with a returned ID for the full source.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | A natural-language question about US building permits or PermitReporter. |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds useful behavior beyond annotations by stating the output is canonical URLs and that full source retrieval requires a fetch call. It also notes the data is 'reviewed' and 'privacy-minimized,' giving the agent context about data quality and scope.
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?
Two sentences with no filler. The search action is front-loaded, the return behavior is stated, and the downstream fetch step is included. Every sentence earns its place.
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?
The tool is simple (one parameter), has safety-relevant annotations, and an output schema exists, so the description does not need to explain return values in depth. It could be more complete by clarifying how it differs from the similarly named 'search_permits' sibling, but the existing description covers the agent's immediate needs.
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 description coverage is 100%, and the schema already documents the single 'query' parameter as a natural-language question about US building permits or PermitReporter. The tool description does not add extra meaning about query formatting, examples, or edge cases, so the baseline of 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 uses a specific verb ('Search') and identifies the exact resource: 'PermitReporter reviewed guidance and privacy-minimized collected building-permit records.' It also clarifies the return type (canonical URLs for citation). It does not explicitly distinguish itself from the sibling tool 'search_permits,' so it falls short of a 5.
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 clear usage context: use this for searching collected permit records and getting citation URLs, then 'Call fetch with a returned ID for the full source.' It provides a concrete next-step routing to fetch, though it does not mention exclusions or how to choose between 'search' and the sibling 'search_permits.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tools have overlapping purposes: `search` and `search_permits` both search for permits, differing only in that `search` also covers guidance. Similarly, `fetch` and `get_permit_record` both retrieve records, with unclear boundary between them. This will cause agent misselection.
Most tools follow a clear `verb_noun` pattern (e.g., `create_permit_watch`, `get_county_coverage`), but `fetch` and `search` are generic and deviate from that pattern, creating a mixed convention. Still, the names are readable and mostly predictable.
With 8 tools, the count is well within the typical 3-15 range and matches the server's scope of permit search, retrieval, and coverage. It feels slightly heavy due to redundant tools, but not excessive.
The tool surface covers search, retrieval, coverage, and leads, but lacks any management of permit watches (no list, update, or delete). This is a notable gap since `create_permit_watch` exists, leaving an incomplete lifecycle.