Skip to main content
Glama
io.github.tammy357/ts-second-opinion

io.github.tammy357/ts-second-opinion

by tammy357

list_reactions

Lists RDB7 test-set reactions with triage verdicts—green (trust), amber (check with DFT), red (re-generate)—to prioritize candidates and filter mirror-repaired guesses.

Instructions

List reactions in the RDB7 test set (1,194 reactions, 8 GoFlow guesses each) with their triage verdict. verdict: 'green' (trust), 'amber' (check with DFT) or 'red' (re-generate). mirror_repaired: filter repaired ones.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_reactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
verdictNo
mirror_repairedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It discloses domain context (dataset size, repeat guesses, meaning of each verdict color) which annotations could not, but it says nothing about ordering, whether output is paginated, how defaults behave, or that the operation is side-effect free beyond the word 'List'.

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?

Three short, front-loaded sentences/fragments with no filler; the dataset scope and the verdict legend come first. The 'verdict:' and 'mirror_repaired:' labels are terse but readable, though the fragment style reads slightly like notes rather than prose guidance.

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

Completeness3/5

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

For a read-only listing tool with four optional parameters and no output schema, the description covers the domain and both meaningful filters but omits pagination semantics and any indication of the result shape or ordering. An agent could call it correctly, but only by guessing how limit/offset behave.

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 0%, so the description must compensate, and it does explain the two non-obvious filters: the verdict enum (green/amber/red with meanings) and mirror_repaired. The two pagination parameters (limit, offset) and their defaults are left entirely undocumented, leaving half the parameters without descriptive support.

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

Purpose4/5

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

The description names a specific verb and resource ('List reactions') scoped to the RDB7 test set, and adds useful framing ('1,194 reactions, 8 GoFlow guesses each') plus the triage verdict concept. It does not distinguish itself from siblings like triage_reaction, triage_batch, or audit_rdb7_dataset, so an agent can't tell from the text alone why it should list rather than triage individually.

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

Usage Guidelines3/5

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

Usage is implied: enumerate reactions together with their verdicts, and optionally narrow by verdict or repair state. There is no explicit when-to-use, when-not-to-use, or pointer to an alternative sibling such as triage_reaction for per-reaction work, so routing must be inferred.

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