Skip to main content
Glama

BondTerminal

Search bonds

bondterminal_search_bonds
Read-onlyIdempotent

Search and screen bonds by free text and REST-compatible filters; optionally return facets. YTM is percent, semi-annual bond-equivalent (S.A.) for every bond; spreads are basis points on the same basis, except EUR bonds, whose spreads are over the Bund curve on the annual basis (spreads.benchmark BUND, yields.ytmAnnual); and prices are per 100 face. Yield conventions: https://bondterminal.com/methodology/yields Page size is capped at 500. Rows give the G-spread as gSpread; oas is a deprecated alias with the same value, not an option-adjusted spread. Billing: 1 read unit per row returned (minimum 1). Basic keys get up to 50 rows per page.

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": "bondterminal_search_bonds"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoFree text: issuer, ticker, ISIN, CUSIP or words in the bond name.
pageNoPaging: size is rows per page; cursor comes from the previous page.
sectorNoIssuer sectors, for example ["Sovereign","Energy"]. Same as filters.sector.
countryNoIssuer countries as two-letter ISO codes, for example ["AR","MX"]. Same as filters.country.
filtersNoScreens, for example country (ISO codes), sector, currency, couponMin/couponMax (percent), maturityDateFrom/maturityDateTo (YYYY-MM-DD), ratingMin/ratingMax, ytwMin/ytwMax (percent) and spreadBpsMin/spreadBpsMax.
include_facetsNoAlso return counts of the matching bonds by field.

Output Schema

NameRequiredDescriptionDefault
rowsYes
cappedNo
facetsNo
warningsNo
nextCursorNo
estimatedTotalNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / country / description
      Added value: +"Issuer countries as two-letter ISO codes, for example [\"AR\",\"MX\"]. Same as filters.country."
    • addedInput schema / properties / filters / description
      Added value: +"Screens, for example country (ISO codes), sector, currency, couponMin/couponMax (percent), maturityDateFrom/maturityDateTo (YYYY-MM-DD), ratingMin/ratingMax, ytwMin/ytwMax (percent) and spreadBpsMin/spreadBpsMax."
    • addedInput schema / properties / include_facets / description
      Added value: +"Also return counts of the matching bonds by field."
    • addedInput schema / properties / page / description
      Added value: +"Paging: size is rows per page; cursor comes from the previous page."
    • addedInput schema / properties / q / description
      Added value: +"Free text: issuer, ticker, ISIN, CUSIP or words in the bond name."
    • addedInput schema / properties / sector / description
      Added value: +"Issuer sectors, for example [\"Sovereign\",\"Energy\"]. Same as filters.sector."
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnly, idempotent, non-destructive); the description adds substantial non-obvious behavior: YTM quoted as percent on a semi-annual bond-equivalent basis, spreads in bps with a Bund/annual exception for EUR, prices per 100 face, gSpread vs the deprecated oas alias, a 500-row page cap, and per-row billing with a 50-row limit for basic keys. These are exactly the details an agent cannot get from annotations.

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?

Purpose is front-loaded in the first clause, followed by dense convention notes where each sentence carries unique operational information (units, alias warning, billing, caps). It is long but nearly all of it earns its place; the methodology URL is a minor bit of leakage.

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?

An output schema exists, so return shape needn't be explained, and the description covers units, pricing conventions, paging caps, and cost. The remaining gap is relational: it never says how this differs from bondterminal_get_bonds or when to prefer it, which matters given 6 parameters and 10 siblings.

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 the baseline is 3, but the description adds real unit semantics the schema omits: the basis on which ytw/spread filters are interpreted (S.A. percent, bps over Bund for EUR) and the effective row cap for basic keys, which constrains page.size behavior beyond the schema's maximum of 500.

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?

States a specific verb (search/screen) and resource (bonds) plus the two capabilities that define it: free-text query and REST-compatible filters, with optional facets. It does not distinguish itself from the sibling bondterminal_get_bonds, which sounds like a plausible alternative for the same resource, so it stops 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.

Usage Guidelines3/5

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

Usage is implied by 'search and screen ... by free text and REST-compatible filters', which tells the agent this is the discovery path. But there is no explicit when-to-use/when-not guidance and no routing to siblings such as bondterminal_get_bonds or bondterminal_get_history, leaving the agent to infer the boundary.

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