Skip to main content
Glama

Tweak a pull

tweak
Read-only

Modify a past pull's stored SQL and rerun it on the same source; the result shows the SQL difference and saves the new pull as a child of the original.

Instructions

Tweak a past pull ('same, but last quarter'): run sql, your change to that pull's stored SQL, on the same source. The reply shows the SQL difference; the new pull is saved as a child of the old one. question is the user's request (defaults to the old). When no definition you were given covers part of the question, say what you assumed in assumptions, one short sentence each ("active customer means an order in the last 90 days"); they're kept with this answer on the user's computer, for them to review and turn into definitions.

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": {
      "pull_id": "<pull_id>",
      "sql": "<sql>"
    },
    "name": "tweak"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlYes
pull_idYes
questionNo
assumptionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior2/5

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

The description adds genuinely useful behavior: the reply shows the SQL diff, and the result is persisted as a child pull, with `assumptions` stored locally for the user to review. However, that persistence side effect sits uneasily with the annotations' readOnlyHint=true, which tells an agent the call only reads. The contradiction is mitigated (additive, non-destructive, original pull untouched) but an agent reasoning from annotations alone would be misled about whether state is written.

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?

Front-loaded with the core action and example, then the diff/persistence outcome, then parameter guidance in a logical order. It is a dense single paragraph with long clauses, but every sentence — including the assumptions example — carries information an agent needs to call it correctly.

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?

No output schema exists, and the description compensates by describing the reply (SQL difference) and the artifact created (child pull). Combined with the parameter explanations, an agent has enough to invoke it; only failure modes and any source-related constraints are unaddressed.

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

Parameters4/5

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

With 0% schema description coverage, the description carries the full burden and largely does: `sql` is defined as the change to the stored SQL, `question` as the user's request defaulting to the old one, and `assumptions` as short single-sentence statements kept with the answer, complete with an example. Only `pull_id` is left implicit ('that pull's stored SQL'), which is minor given the required-parameter pairing.

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?

Names a specific verb and resource (tweak a past pull) and defines the mechanism precisely: run the supplied `sql` against that pull's stored SQL on the same source, producing a new pull saved as a child of the old one. The 'same, but last quarter' example makes the intent concrete and distinguishes it from authoring a fresh query via `query` or `save_pull`.

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?

Clear context for when to reach for it — modifying an existing pull rather than starting from scratch — plus explicit guidance on populating `assumptions` when no given definition covers part of the question. It stops short of naming an alternative tool or stating when not to use it (e.g., when there is no prior pull to derive from).

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