get_subject_classificationRead the current classification state and its decision audit. Confirmed classifications are locked and must not be routinely reassessed.
| Name | Required | Description | Default |
|---|---|---|---|
| subject_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful context beyond annotations by revealing that classifications are locked and that a decision audit accompanies the state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, both purposeful: the first states the operation and output, the second states the locking policy. No filler or redundant restatement of the tool name or title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter read with rich annotations, the description conveys the main returned content: current classification state and decision audit. It does not describe the audit structure or response format in detail, but no output schema exists to fill that gap; this is a minor deficiency given the low tool complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not mention subject_id at all or clarify how it identifies the subject whose classification is read. The schema only provides a required UUID format, so the description fails to compensate for the missing parameter guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Read the current classification state and its decision audit,' which clearly identifies a specific verb and resource. The warning that confirmed classifications are locked distinguishes this lookup from sibling tools like propose_subject_reclassification or reopen_subject_classification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly establishes when this tool is appropriate for reading settled classification state and explicitly says confirmed classifications must not be routinely reassessed. However, it does not name alternative tools or spell out when to prefer this over related reads like get_deliberation or resolve_subject.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools cluster into clear functional families — classification, location, reviews, deliberations, and system — and potentially overlapping operations are explicitly cross-referenced (e.g., enrich_subject vs correct_subject_fact, affirm vs propose reclassification). The main hazard is the resolve_subject / resolve_subject_type / resolve_subject_hierarchy trio, whose near-identical prefixes could mislead an agent at first glance despite well-written descriptions.
The surface is dominated by a consistent snake_case verb_noun pattern with stable verb families: get_*, list_*, resolve_*, set_*, save_*, create_*, register_*, and submit_*. Minor deviations — bare-verb fetch and search, and the noun-led vocabulary_index — break the pattern slightly but do not obscure it.
34 tools is heavy and above the preferred range, and the classification family alone accounts for ten tools with substantially duplicated vocabulary guidance. The count is partially earned, however, because the server genuinely spans several subsystems — reviews, subject classification, location assertions, deliberations, and governance — each with its own lifecycle.
Each subsystem has thorough lifecycle coverage: deliberations (create/claim/contribute/get/list/resolution), reviews (save/fetch/delete/list/visibility), location (assert/list/resolve), and classification (propose/affirm/reopen/relationships/aliases). Minor gaps include no way to edit review content, no direct list-all-subjects endpoint, and no retirement path for fields or aliases.