Skip to main content
Glama

TestGraph

by io.github.BBCBasic

Propose a more precise subject type

propose_subject_reclassification
Idempotent

Submit one independent AI model's evidence-backed refinement to a strict descendant type. One model creates a candidate; agreement by two distinct models automatically moves the subject, confirms and locks it. A locked subject is not reopened by later opinions. Classification vocabulary should represent what a subject fundamentally is. Before creating, selecting, relating or proposing a subject type, identify the semantic head and descriptive modifiers. Material, arrangement/grouping, state/condition, quantity, colour, size, location and purpose/use normally belong in attributes or relationships rather than subject-type names. This is not a simplistic head-noun rule: a compound may remain a distinct type when the combined concept has materially different identity, behaviour, relationships, classification meaning or realistic retrieval needs. The server independently validates structural writes, so client guidance cannot bypass this rule.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reasonYes
evidenceYes
subject_idYes
source_modelYesStable model identity, not the client application name.
target_subject_typeYes
evidence_fingerprintNo

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond annotations by disclosing the candidate/confirmation/lock lifecycle, the two-distinct-model agreement requirement, and the server-side validation that client guidance cannot bypass. These are behavioral details not available in 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 core purpose and lifecycle are front-loaded, and the additional classification-vocabulary guidance is relevant for constructing a valid target_subject_type and reason. It is somewhat long, but each sentence contributes operational or domain context for a complex tool.

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?

The description covers the core lifecycle, locking behavior, and validation constraints, which is strong for a non-read-only operation. However, it omits explicit return/response semantics and some parameter-level details, and no output schema exists to fill that gap.

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

Parameters2/5

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

Schema coverage is only 17% (only source_model is documented in the schema), and the description does not explain individual parameters such as evidence_fingerprint, target_subject_type, evidence, or reason. It gives domain background for subject-type naming but does not compensate for the low parameter coverage.

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 operation: submitting one model's evidence-backed refinement to a strict descendant type. The title and description distinguish it from other classification tools by emphasizing the proposal/lock lifecycle rather than merely reading or affirming classifications.

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?

Provides clear context for when to use the tool: for a single independent model's candidate refinement to a more precise type, with the two-model agreement rule. It includes a when-not (locked subjects are not reopened by later opinions) and broad guidance about semantic heads, though it does not explicitly name sibling tools as alternatives.

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

All TestGraph 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

A3.6/5.0
Disambiguation3/5

Most tools are separated by resource and action, but the classification cluster (affirm_subject_classification, propose_subject_reclassification, reopen_subject_classification, get_subject_classification) and the three resolve_subject* tools require close reading to distinguish. Long descriptions help, but an agent could easily pick the wrong member of those clusters.

Naming Consistency4/5

The dominant pattern is verb_noun in snake_case (create_deliberation, list_reviews_by_visibility, resolve_subject_type, set_review_visibility). Minor deviations such as bare 'fetch' and 'search' and mixed verbs like affirm vs propose vs reopen are readable and do not break the convention.

Tool Count2/5

34 tools substantially exceeds the 25+ threshold even for a server with multiple subdomains. The many classification, type, and location variants add cognitive load, and several could be consolidated or hidden behind a smaller workflow-oriented surface.

Completeness4/5

The set covers the main lifecycles: review save/fetch/assess/delete/visibility, subject resolution/enrichment/correction, classification with voting/reopening, deliberations, locations, and vocabulary management. Minor gaps remain, such as no direct full-subject getter and no update to review text, but these appear intentional in an immutable-review design.

Resources