Brazilian fixed income (CDB, LCI, LCA, CRI, CRA, Tesouro) ranked by net-of-tax and real return.
Scored across 2 tools
The two tools have clearly distinct roles: list_issuers is a reference/filter lookup, while search_bonds performs the actual bond search and ranking. There is no meaningful overlap, and the description of list_issuers explicitly links it to the 'bank' filter of search_bonds.
Both tool names follow a consistent verb_noun snake_case pattern: list_issuers and search_bonds. The convention is predictable and readable throughout.
Two tools is borderline thin for a fixed-income search domain, even though the server appears intentionally narrow in scope. A minimal pair of list/search tools can work, but it leaves little room for common auxiliary operations.
The surface covers issuer discovery and bond search, which are the core read operations. However, there is no get_bond_detail, list_indices, or similar lookup to inspect a specific bond or available index types beyond what search returns, creating notable gaps for a full research workflow.
List the banks/brokers present in the data with their numeric codes and how many bonds each has, to use as the 'bank' filter of search_bonds.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds that results are restricted to banks/brokers 'present in the data' and exposes the returned fields, but says nothing about scope limits, pagination, or how many rows to expect, which is modest added value over the annotations.
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?
A single sentence that front-loads the action, states the payload, and closes with the downstream use case. No filler and nothing redundant with the title.
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?
With no input parameters and no output schema, the description carries the return-value burden and does so by naming the fields returned (numeric codes, bond counts). It omits result size, ordering, and whether the list is exhaustive over the dataset, which would help an agent use the codes correctly.
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?
The tool takes zero parameters, so the baseline of 4 applies. The description correctly implies a no-argument listing and introduces no phantom parameters, though 'the bank filter of search_bonds' presupposes the agent knows that filter's expected value format.
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?
States a specific verb and resource ('List the banks/brokers present in the data') and goes further by describing what each row carries (numeric codes and bond counts). It also names the sibling search_bonds as the consumer of this output, so an agent can route between the two without opening either schema.
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?
Gives clear usage context: call this to obtain values for the 'bank' filter of search_bonds, which is the classic lookup-before-filter pattern. It does not state when not to call it or what to do if the list is empty, so it falls short of a full when/when-not/alternatives statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search active Brazilian fixed-income bonds and rank them. Every bond comes with net_annualized_return (after IR, to maturity) and real_annualized_return (above IPCA), both decimals. 'rate' depends on 'index': cdi* 1.05 = 105% of CDI, cdi+ 0.02 = CDI + 2% a.a., ipca+ 0.06 = IPCA + 6% a.a., pre 0.13 = 13% a.a. fixed. Without an API key the result is a short preview.
| Name | Required | Description | Default |
|---|---|---|---|
| fgc | No | true: only bonds covered by the FGC guarantee (up to R$ 250,000 per CPF per institution). | |
| bank | No | Issuer/broker codes, as listed by list_issuers (e.g. 341 Itaú, 77 Inter, 208 BTG). | |
| index | No | Indexers: cdi* (% of CDI), cdi+ (CDI + spread), ipca*, ipca+ (IPCA + spread), selic*, selic+, pre (fixed rate). | |
| limit | No | How many bonds to return (max 50). | |
| product | No | Product types: cdb, lci, lca, cri, cra, deb (debênture), tpf/td (Tesouro Direto), lf (letra financeira), misc. | |
| sort_by | No | net_return / real_return: highest first. maturity: soonest first. min_investment: lowest first. | net_return |
| tax_free | No | true: only IR-exempt bonds (LCI, LCA, CRI, CRA, incentivized debêntures). false: only taxed ones. | |
| max_years | No | Only bonds maturing within this many years from today. | |
| max_min_investment | No | Only bonds whose minimum investment is at most this amount in BRL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive behavior, so the bar is lower, yet the description adds real context: returned fields (net return after IR, real return above IPCA) and the crucial constraint that without an API key only a short preview is returned. It stops short of describing pagination or result ordering beyond the schema's sort_by.
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?
Front-loaded with purpose, then the return semantics, then the index encoding, then the API-key caveat. Dense but each clause carries information; the encoding sentence is somewhat run-on but not wasteful.
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?
No output schema exists, so the description must carry return-value meaning, and it does by naming the two return fields and their units. With filters fully documented in the schema and safety covered by annotations, only minor gaps (ordering/pagination details) remain.
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 coverage is 100%, so baseline is 3, but the description adds interpretation the schema does not: it decodes how the numeric 'rate' value maps onto each 'index' (cdi* 1.05 = 105% of CDI, ipca+ 0.06 = IPCA + 6% a.a.). That is genuine semantic value beyond the enum listing.
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?
States a specific verb and resource ('Search active Brazilian fixed-income bonds and rank them'), which is clearly distinguishable from the only sibling, list_issuers, that merely enumerates issuer codes. An agent can tell what this tool returns without reading the schema.
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 explains how filters behave (rate/index encoding, preview without an API key) but never states when to choose this tool over list_issuers or gives explicit exclusions. Usage is implied via filter semantics rather than stated, which is the minimum viable level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
list_issuerssearch_bondsBrazilian fixed income & financial data for AI. Selic, CDI, IPCA, CDB/LCI/LCA rankings, FX rates.
Brazilian financial market data (B3): quotes, fundamentals, dividends, REITs (FIIs), BDRs, crypto, F
Your consolidated B3 investment portfolio (the central depository): position by asset, net worth, tr
Brazilian personal & business finance with Open Finance: transactions, cards, investments.
Add one secure layer between your agents and this server.
