Skip to main content
Glama

links_suggest

Surfaces candidate co-evidential particle pairs within a Subject for operator review by comparing embeddings against a similarity threshold. Read-only report that flags unlinked pairs; no mutation.

Instructions

Propose co-evidential candidate pairs within Subjects (read-only).

Within each Subject, ACTIVE particles whose embeddings exceed the
similarity threshold and are not already linked CO_EVIDENTIAL are
surfaced as candidate pairs for operator review. No LLM call, no
mutation — this is the ``REPORT`` mode of ``particles links suggest``.

Args:
    subject_id: Restrict to one Subject. ``None`` scans every
        Subject — prefer passing a ``subject_id`` to keep results focused.
    threshold: Cosine-similarity floor (0.0–1.0). Defaults to
        ``links_suggest.candidate_threshold`` when omitted.
    limit: Maximum candidate pairs to include across all clusters
        (default 100). A ``truncated`` flag is added when the cap fires.

Returns:
    ``{run_at, mode, clusters, total_candidates, warnings}`` matching the
    ``SuggestReport`` schema, optionally with ``truncated: True``.

Input Schema

NameRequiredDescriptionDefault
limitNo
thresholdNo
subject_idNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.210.2

TDQS

A4.7/5.0
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: read-only, no LLM call, no mutation, only ACTIVE particles considered, already-linked CO_EVIDENTIAL pairs excluded, threshold falls back to a named config key, and a `truncated` flag appears when the limit fires. These are exactly the behavioral traits an agent cannot get from schema or annotations.

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 scope statement and mode are front-loaded before the Args/Returns detail, and every line carries information. The docstring-style formatting and cross-reference to `particles links suggest` add a little ceremony but no real waste.

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?

A read-only reporting tool with no annotations and three undocumented parameters is fully specified: what it scans, what it excludes, how the threshold resolves, how truncation surfaces, and even the return shape (with an output schema present, that last part is bonus).

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%, and the description compensates fully: subject_id's None-means-all behavior plus a recommendation, threshold's 0.0–1.0 range and config default when omitted, and limit's meaning (max pairs across all clusters, default 100, triggers truncation).

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: 'Propose co-evidential candidate pairs within Subjects', and immediately scopes it as read-only. The 'within Subjects' framing lets an agent distinguish it from the sibling corpus_links_suggest without opening either schema.

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

Usage Guidelines4/5

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

Gives clear operational context: it is the REPORT mode of `particles links suggest`, produces candidates 'for operator review', and explicitly recommends passing subject_id to keep results focused. It does not explicitly contrast against corpus_links_suggest, so the sibling choice is left to inference from 'within Subjects'.

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