ShotPulled

Log maintenance

log_maintenance

Log a cleaning or maintenance job against a piece of equipment. A task that takes the thing apart opens a calibration epoch, and every recipe locked before it is read through that epoch's offset — so record the offset here if you counted the clicks while reassembling, which is the one moment anybody actually knows it. Read the available tasks, their intervals and their due state from list_grinders.

Input Schema

TableJSON Schema

Name	Required	Description
`note`	No	Optional — what you did, and anything that surprised you
`task`	Yes	Which maintenance job was performed
`details`	No	Fields specific to this task. Which ones a task takes is published as details_fields in the task catalog on list_grinders; a burr clean takes none
`evidence`	No	One line recording what the measurement rested on, e.g. "Counted 6 clicks coarser at reassembly."
`equipment_id`	Yes	The ID of that piece of equipment
`offset_value`	No	The correction, if you measured it now: clicks to ADD to a pre-clean reading to get the same grind today, signed along the collar's own number direction. Omit it and the epoch stays unmeasured, which is a state the app shows rather than a zero it assumes
`performed_at`	No	When it was done (ISO 8601 or YYYY-MM-DD HH:MM:SS, UTC). Defaults to now; backdating is fine
`disturbs_zero`	No	Whether this job disturbed the reference the stored numbers are read against — for a burr clean, whether the burrs actually came out. Defaults to the task's own answer; send 0 for a wipe-down that left the collar alone
`offset_source`	No	How the offset was arrived at: pull (a reference shot), counted (clicks counted at reassembly), typed (asserted directly)
`equipment_kind`	Yes	Which kind of equipment this job was done on

Output Schema

TableJSON Schema

Name	Required	Description	Default
`entry`	Yes
`message`	Yes
`entry_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations only indicate the tool is not read-only, not destructive, and not idempotent. The description adds substantive behavioral context: disassembly opens a calibration epoch, recipes locked before it are read through that epoch's offset, and the offset is only knowable at reassembly. This goes well beyond the sparse annotations, though it could also state the resulting side effects on already-locked recipes more explicitly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with no filler: purpose, calibration-epoch behavior, and a pointer to the task catalog. Each sentence earns its place, and the most important domain nuance (when to record the offset) is explained efficiently.

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?

Covers the tool's purpose, its key behavioral consequence (calibration epoch), and where to discover task options. Combined with a fully described schema and an output schema, an agent has enough to call it correctly. The main gap is not mentioning set_maintenance_offset as the alternative when only the offset needs updating without logging a whole maintenance job.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds real conceptual meaning to offset_value and offset_source by explaining the calibration epoch and why the reassembly moment is the only reliable time to count clicks, which is not fully captured in the schema. It does not need to list individual parameters since the schema documents them thoroughly.

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 description states a specific verb ('Log') and a clear resource ('a cleaning or maintenance job against a piece of equipment'). It immediately distinguishes itself from the sibling read-only catalog tools by telling the agent to get available tasks from list_grinders, and from shot/recommendation logging siblings by the equipment-maintenance focus.

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?

Explicitly instructs the agent to read tasks, intervals, and due state from list_grinders, pointing to the correct sibling for lookup. It gives a concrete condition for when to record the offset (if clicks were counted at reassembly) but does not name or contrast set_maintenance_offset as an alternative for updating an offset outside of a maintenance log.

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

All ShotPulled tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0

Disambiguation4/5

Most tools sort cleanly into register_*, list_*, set_*, and log_* families with clear resource targets. The main ambiguity is between diagnose_shot and diagnose_preview, which are deliberately similar, and between get_dial_state and suggest_next_step, but the descriptions resolve these reasonably well.

Naming Consistency4/5

Naming is overwhelmingly consistent snake_case verb_noun, such as register_coffee, list_shots, update_shot, and set_active. Minor exceptions like kb_changelog next to get_kb_version and grinder_math break the pattern slightly.

Tool Count2/5

With 34 tools, the surface is well over the 25+ too-many threshold. The resource families are individually clear, but the assistant would be easier to navigate with fewer, more consolidated tools or less KB introspection surface.

Completeness3/5

The core dialing workflow is well covered: registration, shot logging, diagnosis, dial state, recipes, and maintenance. However, most registered entities such as grinders, machines, waters, scales, and programs have create+list but no update/delete, and recipes have no unlock/delete lifecycle.

Resources

Need Help?