build_citation_bundleReturn ranked corpus excerpts and canonical URLs for a focused historical or lyrical question. Use this to ground research before interpretation.
| Name | Required | Description | Default |
|---|---|---|---|
| song | No | ||
| limit | No | ||
| query | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / song / enumPrevious value: -[
- "austerlitz-sun",
- "blood-for-blood",
- "broken-mirrors",
- "cheers-to-fritz",
- "discipline",
- "farmington-mourning",
- "gettysburg-ballad",
- "hungry-winter-1780",
- "italy-will-be-made",
- "lancasters-ribbon",
- "leipzig-watch",
- "light-brigade",
- "montreal-smile",
- "old-ironsides",
- "open-blockhouse",
- "rum-alabama-rum",
- "send-the-italian",
- "shiloh-ballad",
- "white-shirts-borodino",
- "the-elephant",
- "tim-and-jones",
- "waterloo-smile"
-]New value: +[
+ "andersonville-prisoner",
+ "austerlitz-sun",
+ "blood-for-blood",
+ "broken-mirrors",
+ "cheers-to-fritz",
+ "discipline",
+ "fare-you-well-my-darling",
+ "farmington-mourning",
+ "gettysburg-ballad",
+ "hungry-winter-1780",
+ "i-havent-found-the-ending-yet",
+ "it-has-to-mean-something",
+ "italy-will-be-made",
+ "lancasters-ribbon",
+ "leipzig-watch",
+ "light-brigade",
+ "montreal-smile",
+ "old-ironsides",
+ "open-blockhouse",
+ "rum-alabama-rum",
+ "send-the-italian",
+ "shiloh-ballad",
+ "some-dreams-only-sleep",
+ "the-elephant",
+ "the-nation-born-at-appomattox",
+ "tim-and-jones",
+ "waterloo-smile",
+ "white-shirts-borodino"
+]Input schema / properties / song / enumPrevious value: -[
- "austerlitz-sun",
- "blood-for-blood",
- "broken-mirrors",
- "cheers-to-fritz",
- "discipline",
- "farmington-mourning",
- "gettysburg-ballad",
- "hungry-winter-1780",
- "italy-will-be-made",
- "lancasters-ribbon",
- "leipzig-watch",
- "light-brigade",
- "montreal-smile",
- "old-ironsides",
- "open-blockhouse",
- "rum-alabama-rum",
- "send-the-italian",
- "shiloh-ballad",
- "the-elephant",
- "tim-and-jones",
- "waterloo-smile"
-]New value: +[
+ "austerlitz-sun",
+ "blood-for-blood",
+ "broken-mirrors",
+ "cheers-to-fritz",
+ "discipline",
+ "farmington-mourning",
+ "gettysburg-ballad",
+ "hungry-winter-1780",
+ "italy-will-be-made",
+ "lancasters-ribbon",
+ "leipzig-watch",
+ "light-brigade",
+ "montreal-smile",
+ "old-ironsides",
+ "open-blockhouse",
+ "rum-alabama-rum",
+ "send-the-italian",
+ "shiloh-ballad",
+ "white-shirts-borodino",
+ "the-elephant",
+ "tim-and-jones",
+ "waterloo-smile"
+]Input schema / properties / song / enumPrevious value: -[
- "austerlitz-sun",
- "blood-for-blood",
- "broken-mirrors",
- "cheers-to-fritz",
- "discipline",
- "farmington-mourning",
- "gettysburg-ballad",
- "hungry-winter-1780",
- "italy-will-be-made",
- "lancasters-ribbon",
- "leipzig-watch",
- "light-brigade",
- "montreal-smile",
- "old-ironsides",
- "rum-alabama-rum",
- "send-the-italian",
- "shiloh-ballad",
- "the-elephant",
- "tim-and-jones",
- "waterloo-smile"
-]New value: +[
+ "austerlitz-sun",
+ "blood-for-blood",
+ "broken-mirrors",
+ "cheers-to-fritz",
+ "discipline",
+ "farmington-mourning",
+ "gettysburg-ballad",
+ "hungry-winter-1780",
+ "italy-will-be-made",
+ "lancasters-ribbon",
+ "leipzig-watch",
+ "light-brigade",
+ "montreal-smile",
+ "old-ironsides",
+ "open-blockhouse",
+ "rum-alabama-rum",
+ "send-the-italian",
+ "shiloh-ballad",
+ "the-elephant",
+ "tim-and-jones",
+ "waterloo-smile"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=true, idempotent=true, openWorld=false, so the safety profile is covered. The description adds genuinely useful output context (ranked excerpts plus canonical URLs) in the absence of an output schema, but says nothing about ranking basis, excerpt size, or what happens when nothing matches.
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?
Two sentences, no filler, and the output contract is front-loaded before the usage cue. Nothing is redundant with the name or 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?
Because there is no output schema, the description should be the authority on what comes back and it does cover the return shape at a high level. It is incomplete on parameters and on failure/empty behavior, which matters for a retrieval tool with a song-scoped corpus.
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 0% across three parameters, so the description must carry the burden and largely fails: 'focused' hints at the 2-80 char query constraint but the `song` enum filter and the `limit` cap of 8 are never mentioned. An agent could call this repeatedly without knowing it can scope results to a specific song.
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 output ('Return ranked corpus excerpts and canonical URLs') scoped to 'a focused historical or lyrical question,' which tells the agent this is a research-grounding read rather than a catalog lookup. It does not name a sibling like search_corpus, so the boundary with the nearest alternative is left implicit.
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?
'Use this to ground research before interpretation' implies a sequencing (retrieve evidence prior to analysis) but gives no exclusion criteria. It never says when to prefer search_corpus or witness_read instead, so the agent must infer the split.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.