Skip to main content
Glama

fit_preview

Read-onlyIdempotent

Preview a planned module fit: stats, fit errors, and a safe install order (Read-only. Pass modules: the complete planned fit for your active ship, one module type ID per fitted module (repeat an ID to fit two). Works anywhere: nothing is fitted, bought or moved. Returns stats with exactly those modules fitted (built from the class base, as a refit would), CPU and power used after your Engineering bonus, slots used per type, and valid plus issues: every reason install_mod or uninstall_mod would refuse the fit, with the same error codes (cpu_exceeded, power_exceeded, no_weapon_slots, no_defense_slots, no_utility_slots, module_limit, module_withdrawn, cargo_capacity_exceeded, personnel_capacity_exceeded), or no_safe_order when every module fits but no step order reaches the fit. For a valid plan, steps lists uninstall_mod and install_mod calls in an order where none is refused for CPU, power, slots or personnel. Cargo limits are checked against your hold as it is now: modules that move into and out of cargo during the steps are not counted, so keep room in your hold; a step marked temporary unfits a kept module that a later step fits again. Fitted modules of a planned type are kept; others are removed. Run the steps yourself, one per tick: each install_mod needs the module in cargo, and docking (or a Ship Maintenance Bay) as usual.)

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": {
      "session_id": "<session_id>",
      "modules": "<modules>"
    },
    "name": "fit_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
modulesYesThe complete planned fit for your active ship: one module type ID per fitted module, repeated to fit more than one. [] previews an empty ship.
session_idYesYour session ID from login/register

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description still adds substantial behavior: it never mutates state, it computes against your current Engineering bonus and the class base 'as a refit would', it enumerates every refusal code install_mod/uninstall_mod would return, and it explains that cargo limits are checked against the hold as it is now. The only gap is that it does not discuss cost, timing, or rate limits, but for a read-only preview that is minor.

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 purpose, then progressively more detailed caveats, and nearly every clause carries operational information (error codes, temporary steps, cargo caveat). It is a single dense parenthetical paragraph, though, and the error-code enumeration plus the 'Read-only' restatement of the annotation could be trimmed.

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

Completeness5/5

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

For a two-parameter read-only tool with no output schema, the description covers return shape (stats, slots per type, valid, issues, steps), failure modes (named error codes), and the execution protocol including the cargo and temporary-step edge cases. Nothing an agent needs in order to call it and act on the result appears to be missing.

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% and the schema description for 'modules' already states it is the complete planned fit with repeated IDs, so the description largely restates it. It does add the framing that this is the complete fit for the active ship rather than a delta, which helps avoid incremental-fit mistakes, but adds no syntax or format detail beyond the schema.

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?

The opening clause names a specific verb and resource — 'Preview a planned module fit' — and enumerates exactly what a preview contains: stats, fit errors, and a safe install order. It is immediately distinguishable from install_mod/uninstall_mod because it makes clear nothing is actually fitted, bought or moved.

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

Usage Guidelines5/5

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

It states when to use it (planning a complete fit for the active ship), that it is safe to run in any state ('Works anywhere: nothing is fitted, bought or moved'), and how it relates to the alternatives — 'Run the steps yourself, one per tick' with the prerequisites that each install_mod needs the module in cargo and docking as usual. That is explicit when/how guidance including the follow-on workflow.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources