delete_shotDelete a logged shot from history. Restores the bean's remaining weight (which is derived from logged doses). Hard delete — there is no undo. To fix a mistake on an otherwise-valid shot, prefer update_shot over delete-and-relog.
| Name | Required | Description | Default |
|---|---|---|---|
| shot_id | Yes | ID of the shot to delete |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| message | Yes | ||
| deleted_shot_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the bar is lower. The description still adds genuinely new behavioral info: the cascade side effect 'Restores the bean's remaining weight (which is derived from logged doses)' and the irreversibility warning 'Hard delete — there is no undo.' No contradiction with idempotentHint, since re-deleting an already-removed shot would simply no-op or fail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each earning its place: purpose, side effect, and alternative routing. The hard-delete warning is front-loaded before the update_shot guidance, and there is zero fluff, repetition, or restatement of the title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The behavioral core is covered: purpose, weight-restoration side effect, irreversibility, and the preferred alternative. The output schema exists so return-value detail is not required. A minor gap is behavior for a non-existent or already-deleted shot_id, but idempotentHint and the output schema mitigate that. For a one-parameter tool, this is complete enough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% — the schema itself documents shot_id as 'ID of the shot to delete.' The description adds no parameter-level detail beyond that (no validation rules, no edge-case handling), so the baseline of 3 applies per the coverage rule.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Delete') with a precise object ('a logged shot from history'), clearly scoping the operation to shot history entries. It distinguishes itself from update_shot by implication, and the title is reinforced rather than merely restated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly routes agents away from destructive misuse: 'To fix a mistake on an otherwise-valid shot, prefer update_shot over delete-and-relog.' This names the exact alternative and the condition that should select it, giving clear when-to-use vs when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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 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.
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.
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.