The disclosures of an issuer in a date range, from the record: signed and receipted (RCO-10060).
Scored across 3 tools
get_filings and resolve_issuer both accept ticker/ISIN/LEI, so an agent could plausibly reach for either when it just wants issuer data; however the descriptions make the boundary clear (one returns the record summary and owning node, the other returns dated filings). list_nodes is clearly distinct.
All three tools follow a clean verb_noun snake_case pattern (get_filings, list_nodes, resolve_issuer) with no style mixing or cryptic abbreviations.
Three tools is on the lean side but each maps to a real step in the workflow: discover nodes, resolve an issuer, pull its filings. Nothing redundant is included, though the surface is small enough that it borders on thin.
The read-only listing lifecycle is covered, but there is no way to filter by filing type or date-type combination beyond a range, and no tool to fetch the actual filing document referenced by the source page — agents hit a dead end after retrieving metadata. Error taxonomy is well specified, which partly offsets the gaps.
get_filings is the disclosures of an issuer in a date range: an issuer by ticker, ISIN or LEI plus a date range returns every filing and release on the record for that issuer in that range, each with its type, its date, its source page and its read date — signed by the node of the issuer's market and receipted. Served from the record as read; nothing new is collected and nothing is inferred. Typed errors: unknown_issuer, ambiguous, not_on_record (per field, per market), invalid_request. Door: https://mcp.getfilings.ai/mcp (routes to the owning node); every node door answers it for its own market.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ISO date, YYYY-MM-DD (inclusive); default today. | |
| from | Yes | ISO date, YYYY-MM-DD (inclusive). | |
| issuer | Yes | Ticker (with exchange where it helps: NASDAQ:AAPL, SHEL.L), ISIN or LEI. | |
| market | No | Optional two-letter market code. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description's value-add here is provenance and failure modes: 'served from the record as read; nothing new is collected and nothing is inferred', plus a concrete enumeration of typed errors (unknown_issuer, ambiguous, not_on_record, invalid_request). That is genuinely useful context beyond the structured fields. It omits result-size limits or pagination behavior, which keeps it from a 5.
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 purpose is front-loaded in the first clause, which is good, but the single sentence is heavily run-on and laced with jargon ('signed by the node of the issuer's market and receipted') that consumes space without informing tool selection. The error list and 'door' URL are useful but would read better as separate, shorter statements.
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 output schema, the description carries the burden of describing returns, and it does list the record fields delivered per filing. The typed error taxonomy further covers failure behavior, which is unusual and helpful. What is missing is any sense of volume (how many filings, any caps) for a date-range query that could span years.
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 100%, so all four parameters are already documented in the schema, establishing a baseline of 3. The description restates the issuer identifier forms (ticker, ISIN, LEI) already present in the schema and adds only the vague 'signed by the node of the issuer's market' framing for the market parameter rather than clarifying its semantics.
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 names a specific verb+resource ('disclosures of an issuer in a date range') and enumerates the returned fields (type, date, source page, read date), so the agent knows exactly what it retrieves. It stops short of distinguishing itself from siblings like resolve_issuer, which matters because the 'ambiguous'/'unknown_issuer' errors imply a resolution step is often needed first.
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?
Usage is only implied: the reader infers this is the endpoint for pulling an issuer's filings once a date range is known. There is no explicit when-to-use versus resolve_issuer, and no guidance on handling the 'ambiguous' error the description itself raises. The 'nothing new is collected' clause hints at read-only lookup scope but is not routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every market node on the roster (nodes.json, region on each), which are live, their regional doors and Agent Cards.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds content-level context — that it reads nodes.json, flags which nodes are live, and includes regional doors and Agent Cards — but says nothing about size, ordering, or caching.
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 dense sentence with no filler, front-loading the resource and then the payload. Some jargon ('regional doors') is left undefined, which costs a point.
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 carries the burden of describing returns; it does name the four content types an agent will receive. It stops short of framing the response shape (array? keyed by region?), leaving a modest gap for a no-param list tool.
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 there is no parameter semantics to explain; the baseline of 4 applies. The description correctly implies no filtering inputs are needed.
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 the resource (market nodes) and enumerates the contents returned: roster entries from nodes.json, live status, regional doors, and Agent Cards. That distinguishes it from get_eco, get_signal, and resolve_issuer, though the verb is implied rather than stated ('Every market node on the roster...').
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?
No statement of when to call this versus the siblings (get_eco, get_signal, resolve_issuer), nor any preconditions. Usage is only inferable from the noun phrase itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find a listed company by ticker, ISIN or LEI: the apex names the owning node and forwards to that node's regional door for the record summary.
| Name | Required | Description | Default |
|---|---|---|---|
| identifier | Yes | Ticker with or without exchange (SHOP, TSX:SHOP, SHEL.L, BHP.AX, D05.SI, NESN.SW, SAP.DE, 7203.T, 005930.KS), ISIN, LEI, an exact legal name or a sourced alias. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior. The description adds genuinely new behavioral context — that the apex node resolves ownership and forwards to a regional node for the summary — but says nothing about failure modes (unknown identifier), latency, or what the summary contains.
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, front-loaded with the purpose before the routing detail, with no filler. The trailing architecture jargon ('apex names the owning node and forwards to that node's regional door') is dense and slightly obscures rather than clarifies.
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 output schema and no annotations covering the return value, the description carries the burden of explaining results, yet only says 'the record summary' without defining it. For a single-parameter lookup the input side is well covered, but the output side and the internal routing metaphor remain under-specified.
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% and the parameter description already spells out ticker formats, ISIN, LEI, exact legal name and sourced alias. The description adds little beyond repeating 'ticker, ISIN or LEI', and in fact omits the legal-name and alias forms the schema supports, so it is baseline at best.
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 gives a concrete verb ('Find') and resource ('listed company') and enumerates the identifier kinds (ticker, ISIN, LEI), so an agent can tell what the tool does. However, it never contrasts itself with the nearby sibling get_record, even though it also mentions returning 'the record summary', leaving some ambiguity about which tool to pick.
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 is for looking up a company from an identifier, but offers no explicit when-to-use guidance, no when-not-to-use, and no comparison to siblings like get_record or list_nodes. The agent must infer that resolution is the entry point to the record summary.
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.
get_filingslist_nodesresolve_issuerThe issuer record as of any date, from the sealed vintage: signed and receipted (RCO-10060).
The auditor of an issuer and every change on the record, dated: signed and receipted (RCO-10060).
The issuer behind a ticker: ISIN, LEI, listing and status, from the record: signed and receipted.
Each market's disclosure regime as one sourced, signed object, with the issuer's ACM-68000 signal.
Add one secure layer between your agents and this server.