Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis — Set Research Interests

set_research_interests

Save separate news and library interest lists collected while interviewing a researcher, so Metis can track relevant news threads, briefings, and literature background.

Instructions

Save the two interest lists after interviewing the person.

NEWS AND LIBRARY INTERESTS ARE SEPARATE THINGS, and either may sit entirely
outside the person's work:

  - `news_interests`    → what they want to know is HAPPENING. Drives the
    story-thread vocabulary (Metis groups news into persistent running
    stories, and a declared interest becomes a subject it can recognise), the
    News surface category tabs, and what the daily and weekly briefings
    monitor. Legitimately includes pure curiosity — following AI policy or a
    conflict closely without ever publishing on it.
  - `library_interests` → what they want a real SCIENTIFIC BACKGROUND on.
    Drives literature relevance and the knowledge layer. Slower and deeper,
    and also allowed beyond current projects: a method they intend to learn
    belongs here before it appears in any of their work.

They overlap, but the differences are the useful part. Do not collapse them.

Neither list requires the person to have any projects or articles. Someone can
join Metis with nothing set up and still have clear interests — ask, do not
infer. Call `start_interest_interview()` for the full interview.

Prefer specific, searchable terms: "sleeping sickness" and "DHIS2" work,
"global health" is too broad to filter anything.

Args:
    news_interests: What the News surface and briefings should track.
        Omit to leave unchanged.
    library_interests: What the literature collection and knowledge layer
        should build on. Omit to leave unchanged.
    role: Optional one-line role description.
    display_name: The name to address them by. Set it when someone new tells
        you their name — without it they are greeted as "Researcher".
    mode: "replace" (default) overwrites; "add" merges into what is there.
    interests: DEPRECATED alias for `library_interests` — the old combined
        field. Accepted so existing callers keep working.
    news_topics: DEPRECATED alias for `news_interests`.

Returns:
    What was saved per list, and what each one now affects.

Input Schema

NameRequiredDescriptionDefault
modeNoreplace
roleNo
interestsNo
news_topicsNo
display_nameNo
news_interestsNo
library_interestsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.6
    • addedInput schema / properties / display_name
      Added value: +{
+  "default": "",
+  "title": "Display Name",
+  "type": "string"
+}
  2. Addedv0.1.5

TDQS

A4.9/5.0
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 so: it discloses the overwrite-vs-merge default ('replace' overwrites; 'add' merges), the omit-means-unchanged semantics per parameter, the deprecated alias mapping, and the fallback greeting behaviour without display_name. It also explains what each list subsequently drives (story-thread vocabulary, briefing monitoring, literature relevance), which is real consequence disclosure rather than restatement.

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?

Purpose and the critical news/library distinction are front-loaded, and the parameter docs are grouped at the end where they belong. It runs long and the 'They overlap, but the differences are the useful part. Do not collapse them.' sentence restates the preceding bullets, though the length is largely justified by seven undocumented parameters.

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?

An output schema exists, yet the description still summarises the return ('what was saved per list, and what each one now affects'). Combined with full parameter semantics, alias handling, and downstream effects, an agent has everything needed to call this correctly on the first attempt.

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 0%, so the description must document all seven parameters and it does — news_interests, library_interests, role, display_name, mode, plus both deprecated aliases with their mappings. It goes beyond naming by adding quality guidance ('specific, searchable terms') and default/omit behaviour for each field.

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 first sentence names a specific verb and resource ('Save the two interest lists') and immediately constrains timing ('after interviewing the person'). The body then splits the resource into two distinct lists with different downstream effects, which is exactly what separates this tool from siblings like start_interest_interview or add_user_topic.

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?

It states the prerequisite context (after an interview), routes the agent to the alternative ('Call start_interest_interview() for the full interview'), and explicitly forbids inference ('ask, do not infer'). It also names an anti-pattern for term selection ('global health' is too broad), which is guidance an agent cannot get from the schema.

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