my quant doesn’t speak english — editorial discovery

by io.github.beepboop2025

Search evidence-bounded stories

search_stories

Read-onlyIdempotent

Find published archive records by text when you do not know an exact story ID. All space-separated terms must match as case-insensitive substrings across IDs, titles, summaries, tags, products, beats, evidence status, contributions, or source labels/release IDs. Returns newest-first stories, normalized query, count, feed receipt, and release identity, preserving evidence clocks and limitations. No relevance ranking or pagination; zero matches returns an empty list. Public and read-only; no credentials. The feed is cached for up to 60 seconds; invalid queries or unavailable/invalid feeds return a tool error. Use get_story for an exact ID or latest_stories for an unfiltered overview.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum matching records to return, newest first; 1–20, default 10. Does not change which terms must match.
`query`	Yes	Plain text, for example "dollar funding" or a source release ID. Unicode NFKC-normalized, trimmed, and whitespace-collapsed; every term must match. At most 12 terms, 160 characters, and 512 UTF-8 bytes after normalization. No quote, Boolean, regex, or semantic-search syntax.

Output Schema

TableJSON Schema

Name	Required	Description
`feed`	Yes	Canonical feed URL, content hash, item count, publication authority, and retrieval timestamp.
`count`	Yes	Number of records returned, not the total number of matches.
`query`	Yes	The Unicode-normalized query with leading/trailing whitespace removed and internal whitespace collapsed.
`schema`	Yes
`release`	Yes	MCP version and deployed source SHA, when available.
`stories`	Yes	Newest-first published records retaining stable IDs, source links, evidence clocks, publication state, release IDs, and limitations.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 6, 2026

addedInput schema / properties / limit / description

Added value: +"Maximum matching records to return, newest first; 1–20, default 10. Does not change which terms must match."

addedInput schema / properties / query / description

Added value: +"Plain text, for example \"dollar funding\" or a source release ID. Unicode NFKC-normalized, trimmed, and whitespace-collapsed; every term must match. At most 12 terms, 160 characters, and 512 UTF-8 bytes after normalization. No quote, Boolean, regex, or semantic-search syntax."

addedOutput schema / description

Added value: +"Published archive records with a feed receipt and deployed MCP release identity. Evidence dates describe the source record; fetched_at describes retrieval, not market freshness."

addedOutput schema / properties / count / description

Added value: +"Number of records returned, not the total number of matches."

addedOutput schema / properties / feed / description

Added value: +"Canonical feed URL, content hash, item count, publication authority, and retrieval timestamp."

addedOutput schema / properties / query / description

Added value: +"The Unicode-normalized query with leading/trailing whitespace removed and internal whitespace collapsed."

addedOutput schema / properties / release / description

Added value: +"MCP version and deployed source SHA, when available."

addedOutput schema / properties / stories / description

Added value: +"Newest-first published records retaining stable IDs, source links, evidence clocks, publication state, release IDs, and limitations."

AddedAug 26, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint: false, and the description adds substantial behavioral context beyond that: public/no-credentials access, 60-second feed caching, error on invalid queries or unavailable feeds, newest-first ordering, and preservation of evidence clocks and limitations. It also explicitly states the absence of relevance ranking and pagination. No contradiction with annotations.

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

Conciseness5/5

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

The description is dense but every sentence earns its place: matching semantics, result shape, behavior on empty/error cases, caching, and routing to siblings are all covered without filler. The primary action and trigger are front-loaded in the first sentence, followed by operational details an agent needs before calling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, the annotations, and the output schema, the description is complete: it covers when to use it, what inputs mean, what outputs include, failure modes, caching, and alternatives. An agent has everything necessary to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description still adds valuable parameter semantics: it defines how query terms are interpreted (case-insensitive substrings, space-separated, all must match), the fields searched, normalization behavior, term/character/byte limits, and absence of quote/Boolean/regex syntax. It also clarifies that limit only caps results and does not change matching behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Find published archive records by text' and explicitly states the trigger condition 'when you do not know an exact story ID.' It also names sibling tools for contrast (get_story, latest_stories), so an agent can distinguish this tool from alternatives without inspecting their schemas.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use guidance: text search when the exact ID is unknown. It also names alternatives directly: 'Use get_story for an exact ID or latest_stories for an unfiltered overview.' It further notes no pagination and the empty-list behavior for zero matches, making invocation expectations clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All my quant doesn’t speak english — editorial discovery tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.