Skip to main content
Glama

evaluate_plans

Compare competing feature plans, select the winning approach automatically or manually, and use that plan for implementation.

Instructions

Evaluate competing plans for a feature and select the winner. The winning plan's approach will be used for implementation.

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": {
      "projectDir": "<projectDir>",
      "featureId": "<featureId>"
    },
    "name": "evaluate_plans"
  }
}

Input Schema

NameRequiredDescriptionDefault
featureIdYesID of the feature to evaluate plans for
projectDirYesAbsolute path to the project directory
manualSelectionNoOverride automatic selection with manual choice
selectionReasonNoReason for manual selection

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
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 disclosure burden. It does add genuine behavioral value by stating the consequence of selection (the winning plan drives implementation), but it omits whether the selection is persisted, what happens on ties or invalid plans, and whether a manual override changes the semantics.

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?

Two short sentences, no filler, with the action front-loaded before the downstream consequence. Slightly under-specified rather than verbose — the brevity costs coverage rather than wasting words.

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?

With no annotations and no output schema, the description must explain return values, but it never says whether the tool returns the winning plan, an evaluation report, or just a status. It also leaves the automatic-vs-manual selection logic unexplained, which is the tool's most distinctive behavior for a four-parameter mutation-like operation.

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 description coverage is 100%, so all four parameters are already documented, making 3 the baseline. The description adds no parameter-level meaning, and notably never mentions that manualSelection/selectionReason let a caller override the automatic winner, which is the one behavioral nuance the schema alone does not convey.

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 states a specific verb and resource ('Evaluate competing plans for a feature and select the winner'), which is far more informative than the bare name. It does not name or differentiate itself from any sibling (e.g., check_reviews, configure_plan_mode), so an agent cannot rule out an overlapping tool from the text alone.

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 only implied: the second sentence ('The winning plan's approach will be used for implementation') signals this happens after plans exist and before implementation. There is no explicit statement of prerequisites (plans must already have been generated), no when-not-to-use clause, and no named alternative for reviewing or comparing plans differently.

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