Skip to main content
Glama

court_verify_evidence

Verifies verbatim quotes, AST citations, and command exhibits deterministically before submission, ensuring evidence is valid for adversarial review.

Instructions

Bailiff deterministic verification for verbatim quotes, AST citations, or command exhibits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "exhibit": "<exhibit>"
    },
    "name": "court_verify_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
exhibitYes
repo_rootNo
source_lookupNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations at all, the description carries the full behavioral burden and delivers very little. 'Deterministic' hints that results are reproducible and side-effect free, but that is inference, not disclosure; nothing states whether the tool reads files, executes commands, mutates the repo, or how errors are surfaced. For a tool with a nested free-form exhibit parameter and no output schema, this leaves an agent guessing about side effects and failure modes.

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?

A single front-loaded sentence with no filler or repetition. Its brevity is appropriate in form, though the terseness borders on under-specification rather than genuine economy.

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 three undocumented parameters including a nested object, no annotations, and no output schema, the definition should do substantially more work. An agent knows the tool 'verifies evidence' but not what to put in the exhibit, what repo_root does, or what a successful versus failed verification looks like.

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 description coverage is 0% across three parameters, one of which is a required nested object ('exhibit') and one of which ('source_lookup') is opaque. The phrase 'verbatim quotes, AST citations, or command exhibits' vaguely gestures at exhibit variants but never maps them to fields, shows an exhibit shape, or explains the roles of repo_root and source_lookup. The description does not compensate for the schema gap.

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

Purpose3/5

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

The description names a specific verb ('verification') and object ('evidence') and enumerates three evidence kinds (verbatim quotes, AST citations, command exhibits), which helps distinguish it from siblings like court_challenge or court_replay_gate. However, 'Bailiff deterministic verification' is unexplained jargon, and an agent cannot tell from this text what verification actually means in practice (comparison against source? re-execution? structural parse?).

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 statement of when to call this versus court_challenge, court_replay_gate, or court_judge, all of which sound adjacent to evidence checking. No prerequisites, no mention of when verification should be skipped or repeated, and no indication of what a caller should do with a failure result.

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