Skip to main content
Glama
bzdOS

hubd

by bzdOS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

hub_recall

Retrieve ranked project data across cards, decisions, and tasks using deterministic scoring for relevance and recency, with staleness flags to prevent outdated facts.

Instructions

What do we know about X — ranked across project cards, their sections, decisions, the journal and tasks, instead of hub_search's flat exact-substring list or hub_get's everything-about-one-project. Scoring is deterministic and readable: term coverage first, then where the line lives (a decision outranks a passing note), then recency. EVERY hit carries the date it was true as of and a stale flag — recall's real failure mode is handing over a two-month-old fact with this morning's confidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoreturn everything, uncapped. By default long lists are trimmed to fit an agent context and what was left out is reported in `truncated`.
limitNodefault 20
queryYeswords that name the thing; stop-words (the, not, of, and their Russian counterparts) are dropped and listed back as `dropped`; a term matches at the start of a word, never inside one
projectNoonly this project — a slug, or several comma-separated
staleDaysNoa hit older than this is flagged stale, default 30

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.15
    • addedInput schema / properties / project
      Added value: +{
+  "description": "only this project — a slug, or several comma-separated",
+  "type": "string"
+}
    • addedInput schema / properties / query / description
      Added value: +"words that name the thing; stop-words (the, not, of, and their Russian counterparts) are dropped and listed back as `dropped`; a term matches at the start of a word, never inside one"
  2. Addedv0.9.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does: it discloses the deterministic ranking stages (term coverage, line provenance, recency), the staleness mechanism with its resulting 'stale' flag, and the tool's real failure mode (old facts presented with fresh confidence). This is unusually rich behavioral context.

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?

Front-loaded with the purpose, then scoring, then staleness. Efficient overall, though the closing failure-mode sentence is a narrative flourish that is a touch long for a tool definition.

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?

No output schema, so the description must convey the return shape; it explains that every hit carries an as-of date and a stale flag, and the schema covers truncation. It stops short of describing the full hit structure, but is sufficient to call the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents query tokens, full/limit/project/staleDays behavior and the truncated/dropped reporting. The description adds no parameter detail beyond that, so the baseline of 3 applies.

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?

States a specific verb and resource — recall what the hub 'knows about X' — and enumerates the ranked sources (project cards, sections, decisions, journal, tasks), explicitly contrasting with both hub_search and hub_get. An agent can distinguish it from siblings without opening a schema.

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?

Names two alternatives and their behaviors: hub_search's 'flat exact-substring list' and hub_get's 'everything-about-one-project'. The condition that selects this tool (wanting ranked, relevance-ordered recall) is clear from the contrast.

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

Deploy Server

Other Tools