FTS5 search across the permit corpus (jurisdictions, rebates, templates).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | FTS5 query across jurisdictions, rebates, templates. | |
| record_type | No | Optional filter to a single record type. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It reveals that this is an FTS5 search, which implies full-text matching semantics and a read-only nature, and it scopes the corpus to three record types. It does not mention return shape, ordering, or any caveats, but for a search tool the core behavior is reasonably transparent.
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 a single, front-loaded sentence with no filler. It states the verb, scope, and the exact record types covered in minimal characters.
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 simple schema and absence of output schema, the description is sufficient for a basic invocation but omits useful context such as expected return values, FTS5 syntax nuances, and guidance relative to sibling tools. It is functional but minimal.
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 67%: query and record_type are documented in the schema, while limit is not. The description adds only the phrase 'permit corpus' and the three record types, which largely echoes the schema. No extra parameter-level guidance is provided.
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 clearly identifies the action ('FTS5 search') and the resource ('permit corpus') with explicit record categories: jurisdictions, rebates, templates. However, it does not differentiate itself from sibling tools like permit_lookup or jurisdiction_index, 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 implies the tool should be used when performing full-text search across permit-related records, but it provides no explicit guidance about when not to use it or which sibling tools might be better for specific lookups. The use case is inferable, but not stated.
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.
Several tool pairs overlap heavily: permit_lookup, search_permits, and jurisdiction_index all address permit discovery, while web_policy_history and enclosure_evidence_pack both track the same robots.txt/ai.txt/llms.txt/TDM-Rep policy surface. Agents would need to read very long descriptions carefully to avoid selecting the wrong tool.
All names are snake_case but the pattern is mixed: most are noun phrases like agent_census_stats and web_policy_history, while request_quote, search_permits, and verify_contractor_license use verb-first naming. The names are readable but do not follow one consistent convention.
Fifteen tools is at the high end of a reasonable scope, and the set spans permits, datacenter indices, agent attestations, web policy history, and quote requests. The count is not absurd, but it feels like several different products bundled into one server.
The permit lookup/search/rebate/contractor side is reasonably covered for read-only queries, and there is useful verification and attestation tooling. However, the 'Agent Market' side has no way to browse or complete a purchase beyond one request_quote action, and some data products like datacenter and agentic commerce feel disconnected from the core permits domain.