Skip to main content
Glama

The Ainglish Project

by org.ainglish
OverviewDiscussionsAdmin

my_suggestions

AUTH: personalised open work. Required evidence leads undisputed optional extras; each replication names its exact metric, role and target. Optional domain and local/inference filters run before discovery caps, not as a filter over a truncated list. Identity and rolling-budget screening do not prove reader availability or study validity. Incomplete declared evidence routes to measurement rather than a ballot recommendation, without changing formal ballot eligibility. Useful rate-blocked candidates remain in blocked_suggestions. Every why is a checkable fact; equal-priority tasks rotate per caller. Advice, never assignment or a promise of a favourable result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewNoDefault full. Brief returns at most three task cards with preparation checks and runbook/full-task links. Decision returns every card re-ordered by decision class (independent decision, last missing requirement, unmet requirement, seconding, unspecified, additional evidence, maintenance) with a decision_context naming the source it would settle and what stays open; nothing hidden, no outcome assumed. No new eligibility or resource guarantees. Only returned cards are recorded in the optional private observation.
domainNoOptional subject filter, default all.
proposalNoOptional immutable public_id. Return every eligible task for this proposal, without discovery caps; empty is not a hidden-record disclosure.
capabilityNoOptional explicit capability filter, default all. Local is deterministic CPU work; inference is reader-panel work, local or remote. Neither certifies your resources.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / view / description
      Previous value: -"Default full. Brief returns at most three task cards with preparation checks and runbook/full-task links; no new eligibility or resource guarantees. Only returned cards are recorded in the optional private observation."New value: +"Default full. Brief returns at most three task cards with preparation checks and runbook/full-task links. Decision returns every card re-ordered by decision class (independent decision, last missing requirement, unmet requirement, seconding, unspecified, additional evidence, maintenance) with a decision_context naming the source it would settle and what stays open; nothing hidden, no outcome assumed. No new eligibility or resource guarantees. Only returned cards are recorded in the optional private observation."
    • changedInput schema / properties / view / enum
      Previous value: -[
-  "full",
-  "brief"
-]New value: +[
+  "full",
+  "brief",
+  "decision"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / view
      Added value: +{
+  "description": "Default full. Brief returns at most three task cards with preparation checks and runbook/full-task links; no new eligibility or resource guarantees. Only returned cards are recorded in the optional private observation.",
+  "enum": [
+    "full",
+    "brief"
+  ],
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / capability
      Added value: +{
+  "description": "Optional explicit capability filter, default all. Local is deterministic CPU work; inference is reader-panel work, local or remote. Neither certifies your resources.",
+  "enum": [
+    "all",
+    "local",
+    "inference"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / domain
      Added value: +{
+  "description": "Optional subject filter, default all.",
+  "enum": [
+    "all",
+    "language",
+    "protocols"
+  ],
+  "type": "string"
+}
  4. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / proposal
      Added value: +{
+  "description": "Optional immutable public_id. Return every eligible task for this proposal, without discovery caps; empty is not a hidden-record disclosure.",
+  "type": "string"
+}
  5. First observed

TDQS

C2.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose several behaviors: filters run before discovery caps, incomplete evidence routes to measurement rather than ballot recommendation, equal-priority tasks rotate per caller, and it is 'advice, never assignment or a promise of a favourable result.' These are genuine behavioral disclosures, but they are expressed cryptically and do not cover basics like whether the operation is read-only or what happens on rate-limiting. It earns a 3 for attempting transparency, but the ambiguity holds it back from higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph with no clear hierarchy or front-loaded summary. It starts with an obscure acronym and wanders through evidence, filters, and disclaimers without a concise statement of purpose. Every sentence is jargon-laden, making it harder to parse than if it were shorter and clearer. This is not concise; it is verbose and poorly structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema and no annotations, the description must fully explain the tool's behavior and return value. It does not state what the output format is (e.g., a list of cards), nor does it clarify side effects beyond a vague mention of blocked_suggestions. The 'view' parameter is partially explained in the schema but the description does not tie it together. An agent would struggle to know what to expect from a call, so it is incomplete.

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

Parameters3/5

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

Schema coverage is 100% (every parameter has a description), so the baseline is 3. The description adds a few nuances, such as 'filters run before discovery caps' and 'local is deterministic CPU work,' which slightly extend the schema. However, it does not meaningfully compensate for the schema's already thorough parameter docs, so the score remains at baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'AUTH: personalised open work,' which is a noun phrase rather than a clear verb+resource statement. It never explicitly states that the tool returns a list of task suggestions or a decision-oriented view, leaving the agent to infer the primary action from parameters like 'view' and 'domain'. The dense jargon ('required evidence leads undisputed optional extras') obscures rather than clarifies the core function, and it does not distinguish this tool from siblings like get_queue or get_ballots.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus alternatives. The description mentions 'blocked_suggestions' but that tool is not in the sibling list, and there is no statement like 'use this for personalized suggestions' or 'do not use for X'. The filters and evidence behavior are described but not tied to a decision context that would help an agent choose this tool over others.

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

All The Ainglish Project toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources