Skip to main content
Glama

Search planning decisions

search_pipeline_decisions
Read-onlyIdempotent

Search council, planning commission and zoning board decisions by place, body, action and meeting date. RECOMMENDED_* is a recommendation, not a final decision. A decision does not guarantee construction. Coverage varies by source and place; an empty result does not establish that no record exists. Up to 25 results per call. total_capped marks a lower bound; total_unknown means the total is unknown. Pagination guidance is in _notes.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_pipeline_decisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoDeciding body, partial ('Planning Commission', 'Zoning')
cityNoCity name (matches the address city or the deciding jurisdiction)
pageNoPage number, 1-based (default 1)
startNoInstead of page: 1-based position of the first result to return, e.g. start=24 continues after result 23 (as named in `_notes`)
stateNo2-letter state code
linkedNotrue: only items linked to a planning case we hold
addressNoStreet address named in the item, partial
outcomeNoNormalised action: APPROVED, DENIED, RECOMMENDED_APPROVAL, TABLED, ...
land_useNo'only' (default): land-use items; 'all': every stored itemonly
per_pageNoResults per page (default 25, max 25)
case_numberNoA case number named in the item (formatting ignored)
matter_fileNoThe clerk's file number
land_use_typeNo
meeting_afterNo
meeting_beforeNo
jurisdiction_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations already establish a safe, idempotent read, and the description goes well beyond them: it caps results at 25 per call, explains that total_capped is a lower bound while total_unknown means the total is unknown, warns that coverage varies by source and place, and states that an empty result does not prove no record exists. It also pre-empts misinterpretation of data semantics (a RECOMMENDED_* action is not a final decision; a decision does not guarantee construction), which is exactly the context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core capability is front-loaded in the first sentence and the caveats follow as short, discrete clauses. Every clause carries information, though the run of caveats is slightly list-like and could be grouped to make the interpretive warnings easier to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter, zero-required search with no output schema, the description covers the important unknowns: result cap, total-field caveats, pagination pointer to _notes, and coverage limits. It stops short of describing what a result item contains, but the total/pagination notes and interpretive warnings cover most of what an agent needs to call and trust it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, so the baseline would be 3, but the description adds real meaning the schema does not: it explains the RECOMMENDED_* prefix used in the outcome enum and frames the filters as place/body/action/date. It does not clarify the land_use 'only' vs 'all' scope tradeoff or the page-vs-start relationship, which remain schema-only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource (search ... decisions) plus the deciding bodies and the facets used to narrow (place, body, action, meeting date). It clearly separates this from record-lookup siblings by scoping to council/planning-commission/zoning-board decisions, though it never names search_pipeline_cases, so an agent must infer that cases and decisions are different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the enumerated filters and the note that pagination guidance lives in _notes, which tells the agent how to continue a result set. There is no explicit when-to-use/when-not guidance and no routing to search_pipeline_cases or get_pipeline_case, so the agent has to reason about which sibling covers cases rather than decisions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources