Skip to main content
Glama

Scholar Feed

by io.github.YGao2005

Create Watch

create_watch

Create a standing watch — evaluated daily against newly-indexed papers, surfacing new matches via the email digest and via check_watches. MUTATES. Get-or-create by name (re-creating with an existing name returns it unchanged — never errors on duplicate). TWO forms: (1) the v2 STRUCTURED filter via criteria (collections/authors/categories/text/has_code/min_novelty/similar, AND-composed) — the composable, agent-tunable form, recommended; tune it with preview_watch first, and edit later with update_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. (2) a single legacy seed selector (q OR collection_name OR collection_id OR anchor_paper_id); if criteria is given it takes precedence. Requires SF_API_KEY.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSemantic/keyword topic seed. One seed selector only.
nameYesLabel for the watch, e.g. 'novel KV-cache work'.
categoryNoWatch an arXiv category (e.g. 'cs.LG'), filtered by novelty_min. One seed selector only.
criteriaNov2 STRUCTURED filter (collections/authors/categories/text/has_code/min_novelty/similar). When provided, this defines the watch (kind='filter') and the single-selector seeds above are IGNORED. This is the composable, agent-tunable form — call preview_watch first to tune it.
author_idNoWatch an author's new work, by author ID. One seed selector only.
novelty_minNoOnly surface papers at/above this novelty score (0..1). The signal/noise knob — raise it for 'only tell me when it matters'. Default 0.5.
recency_daysNoFor a structured (criteria) watch: only consider papers from the last N days (default 7; the 'cites' relation uses 30).
collection_idNoWatch the neighborhood of a collection by UUID. One seed selector only.
anchor_paper_idNoWatch papers similar to this arXiv ID. One seed selector only.
collection_nameNoWatch the neighborhood of a collection by name (resolved by the backend). One seed selector only.
scope_to_citations_ofNoWatch new papers citing this arXiv ID. One seed selector only.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okNoTrue when the operation succeeded.
watchNoThe created/affected watch, when applicable.
actionNoMachine label: saved | no_change | removed | liked | created | updated | deleted.
messageNoHuman-readable summary of the outcome.
arxiv_idNo
collectionNoThe created/affected collection, when applicable.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

The description clearly states MUTATES, get-or-create semantics, duplicate handling ('never errors on duplicate'), criteria precedence, default ranking behavior, and the requirement for SF_API_KEY. Annotations only indicate readOnlyHint=false and destructiveHint=false, so the description adds meaningful behavioral context. Minor gap: it doesn't describe what the response contains, but an output schema exists.

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?

The description is dense but organized: it front-loads the core purpose and mutation warning, then explains get-or-create, then the two forms and their trade-offs. Every sentence carries meaningful guidance. It is long because the tool has two forms and many parameters, but it earns its length; a small amount of redundancy (e.g. repeating that criteria is recommended) exists.

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?

For an 11-parameter tool with nested objects, a full output schema, and many siblings, the description provides comprehensive context: how to choose between forms, what the default ranking is, how to tighten it, get-or-create semantics, auth requirements, and how it relates to preview_watch/update_watch/check_watches. No critical operational guidance is missing.

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

Parameters4/5

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

Schema coverage is 100%, so parameters are already well documented. The description adds valuable semantic guidance beyond the schema: explaining which fields are AND-composed, that criteria takes precedence over legacy seeds, the 'rising' default rationale, and the anti-noise min_impact_pct usage. Some structured sub-fields (e.g. collections.relation) are more detailed in the schema than the description, but the description adds enough to justify above-baseline.

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 states a specific verb ('Create'), a resource ('standing watch'), and its core behavior (evaluated daily against newly-indexed papers, surfacing matches via email digest and check_watches). It also distinguishes the v2 structured form from the legacy seed form, clearly separating this from siblings like preview_watch and update_watch.

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 explicitly says when to use the structured criteria form (recommended, agent-tunable), advises tuning with preview_watch first, points to update_watch for later edits, and notes the get-or-create duplicate behavior. It also explains when the legacy seed selector applies and that criteria takes precedence, giving clear usage direction.

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

All Scholar Feed toolsInspect
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.

TDQS

A4.3/5.0
Disambiguation4/5

Most tools target a distinct resource and action — search vs. saved-library synthesis vs. citation analysis vs. article metadata — and the descriptions explicitly cross-reference one another to reduce confusion. A few retrieval/analysis tools (get_field_orientation, get_foundational_lineage, get_citations, check_drift) have adjacent purposes and could be misselected without reading their descriptions carefully.

Naming Consistency4/5

The overwhelming majority follow a clear verb_noun snake_case pattern: create_watch, delete_watch, list_library, save_paper, annotate_paper, fetch_fulltext, search_papers. Minor deviations like co_author_graph and the interchangeable retrieval verbs (search, find, get, check, ask) create slight inconsistency, but the overall convention is predictable.

Tool Count3/5

27 tools is on the heavy side, but the server covers several coherent subdomains: search/discovery, library/collection management, watches, annotations, and research analysis. The count is justifiable for the broad purpose, though some of the discovery/analysis tools could likely be consolidated or split into a separate server.

Completeness4/5

The tool surface covers the core lifecycle well: search, fetch, save, organize into collections, annotate, watch for new papers, and analyze citations/authors/gaps. Minor gaps exist — there is no collection deletion/rename, no explicit mark-as-read tool, and no unlike operation — but these are workable edge cases rather than blocking omissions.

Resources