Skip to main content
Glama

District Listings

Search District Listings

search_listings
Read-onlyIdempotent

Searches District's published, operator-committed London office listings for a team, by the number of desks, an area (for example Fitzrovia) and, optionally, the month the team wants to move in (startMonth, YYYY-MM) and a maximum budget. Only the area, the number of desks and a budget, where given, leave a listing out; the start month ranks results and does not remove one, so a returned listing can miss it. Returns count (listings that meet the area and team size, and the budget where given) and matchCount (those that match everything asked). Each listing has its operator's public name, desk range, published price and price for each commitment length the operator has set, a one line availability summary with its status, the days it was last confirmed, misses (what it misses of what was asked; a listing with any misses is not counted in matchCount and is not a match for everything asked) and url, its District listing page, where viewings are requested and enquiries are made. Read only: it cannot book a viewing, make an enquiry or show contact details.

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_listings"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoOne London area or neighbourhood, e.g. 'Fitzrovia'
areasNoSeveral London areas, e.g. ['Shoreditch','Clerkenwell'] (max 5); treated as alternatives
desksNoNumber of desks the team needs
limitNoMaximum listings to return (default 20)
seatsNoThe same as desks; use desks
startMonthNoMonth the team wants to move in, as YYYY-MM, e.g. 2027-01. Ranks listings; never removes one
budgetBasisNoBasis the budget is quoted in; defaults to desk_month
maxBudgetMinorNoMaximum budget in pence (e.g. 60000 = 600 pounds)

Output Schema

NameRequiredDescriptionDefault
countYesTotal listings that meet the area and team size given (and the budget, where given)
listingsYes
matchCountYesHow many of them match everything asked: the listings whose misses is empty

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations' readOnly/idempotent/closed-world profile, the description discloses concrete limits ('it cannot book a viewing, make an enquiry or show contact details') and, more importantly, the semantics of the two counts: count is area+desks(+budget) while matchCount requires everything asked, and 'a listing with any misses is not counted in matchCount'. That is the kind of non-obvious behavioral context annotations cannot express.

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

Conciseness3/5

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

Purpose is correctly front-loaded in the first sentence, but the middle passage enumerates listing fields ('operator's public name, desk range, published price and price for each commitment length ... misses ... and url'), which an output schema already covers, and the sentences are long, clause-heavy and hard to scan. Several phrases repeat ideas already stated (misses/matchCount is explained twice).

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 an 8-parameter, zero-required search tool with full schema coverage and an output schema, the definition covers filtering logic, ranking behavior, result-count semantics and side-effect limits. Its remaining weakness is redundancy rather than omission: return-field detail duplicates the output schema, and the desks/seats alias and budgetBasis options are not clarified.

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 100%, so a baseline of 3 is warranted, but the description genuinely adds meaning: it establishes which inputs exclude listings versus which merely rank them, and ties the budget to the 'where given' conditional. It does not explain the budgetBasis enum options or the desks/seats aliasing, so the added meaning is real but partial.

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 definition opens with a specific verb and a tightly scoped resource: 'Searches District's published, operator-committed London office listings for a team, by the number of desks, an area ... and ... budget'. The qualifiers 'published' and 'operator-committed' rule out a large class of listings an agent might otherwise expect. It does not name or contrast with the sibling tools get_listing and get_availability, so the differentiation is implicit rather than explicit.

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

Usage Guidelines4/5

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

The description gives real invocation guidance: 'Only the area, the number of desks and a budget, where given, leave a listing out; the start month ranks results and does not remove one', which tells the agent exactly how each input affects the result set and prevents it from treating startMonth as a filter. It does not state when to prefer this tool over get_listing or get_availability, so routing to siblings is left to inference.

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