Nestling

Log feed

create_feed

Add a feed to the baby's Nestling log: breastfeeding (with duration and side), bottle (with amount in ml), solids, or expressing. Use this only when the user asks to log or record a feed. Each call adds a new entry, so do not retry after success. Accepts ISO 8601 ("2026-05-07T20:00:00Z"), relative ("2 hours ago", "now"), day and time ("today 3pm", "yesterday 8:30pm"), time only ("3pm"), or date and time ("2026-05-07 8pm"). Times without a zone use the timezone argument.

Input Schema

TableJSON Schema

Name	Required	Description
`side`	No	Breast side, for breastfeeding or expressing
`type`	Yes	Feed type
`notes`	No	Optional notes (max 10,000 characters)
`babyId`	Yes	The baby's ID from list_babies
`amountMl`	No	Amount in millilitres (max 5000)
`timezone`	No	The user's IANA time zone, such as "Europe/London". When left out, the host's location hint is used if it sends one, else UTC.
`timestamp`	Yes	When the feed happened (for breastfeeding, when it started)
`durationSeconds`	No	Duration in seconds

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`totalResults`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 5, 2026

changedInput schema / properties / babyId / description

Previous value: -"The baby's UUID"New value: +"The baby's ID from list_babies"

changedInput schema / properties / notes / description

Previous value: -"Optional notes (max 10,000 chars)"New value: +"Optional notes (max 10,000 characters)"

changedInput schema / properties / side / description

Previous value: -"Which side (for breastfeeding)"New value: +"Breast side, for breastfeeding or expressing"

changedInput schema / properties / timestamp / description

Previous value: -"When the feed happened: Date/time — accepts ISO 8601 (\"2026-05-07T20:00:00Z\"), relative (\"2 hours ago\", \"now\"), day+time (\"today 3pm\", \"yesterday 8:30pm\"), time-only (\"3pm\"), or date+time (\"2026-05-07 8pm\")"New value: +"When the feed happened (for breastfeeding, when it started)"

addedInput schema / properties / timestamp / maxLength
```
Added value: +100
```
addedInput schema / properties / timestamp / minLength
```
Added value: +1
```

addedInput schema / properties / timezone

Added value: +{
+  "description": "The user's IANA time zone, such as \"Europe/London\". When left out, the host's location hint is used if it sends one, else UTC.",
+  "maxLength": 64,
+  "type": "string"
+}

addedOutput schema / properties / data / properties / at

Added value: +{
+  "description": "When the entry happened, ISO 8601 UTC",
+  "type": "string"
+}

addedOutput schema / properties / data / properties / localTime

Added value: +{
+  "description": "The same time in the time zone used, with the zone name",
+  "type": "string"
+}

addedOutput schema / properties / data / properties / timezone

Added value: +{
+  "description": "Time zone used to read the times given",
+  "type": "string"
+}

Changed4 schema fields changedMay 29, 2026
- changedInput schema / properties / amountMl / description
```
Previous value: -"Amount in millilitres"New value: +"Amount in millilitres (max 5000)"
```
- addedInput schema / properties / amountMl / maximum
```
Added value: +5000
```
- changedInput schema / properties / notes / description
```
Previous value: -"Optional notes"New value: +"Optional notes (max 10,000 chars)"
```
- addedInput schema / properties / notes / maxLength
```
Added value: +10000
```
First observedMay 27, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the mutation profile is known. The description adds the operational consequence of non-idempotency ('each call adds a new entry, so do not retry after success') and spells out the timestamp formats the tool will parse, which is genuinely extra context.

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 purpose, then usage gate, then timestamp formats. Three sentences with no filler, though the long parenthetical list of time formats makes the final sentence dense; it earns its place by preventing malformed timestamp calls.

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 non-idempotent create tool with an output schema, full parameter coverage and annotations, this is complete: the agent knows what it writes, when to call it, not to retry, and how timestamps are interpreted. Return values are covered by the output schema.

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 coverage is 100%, so the baseline is 3, but the description goes beyond it by enumerating the accepted timestamp input formats (ISO 8601, relative, day-and-time, time-only, date-and-time) and noting that zoneless times fall back to the timezone argument — real added meaning for the least obvious required parameter.

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?

States a specific verb and resource ('Add a feed to the baby's Nestling log') and enumerates the exact feed subtypes (breastfeeding, bottle, solids, expressing), which cleanly separates it from siblings like create_nappy and create_sleep without the agent opening a schema.

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?

Gives a clear when-to-use gate ('Use this only when the user asks to log or record a feed') and an operational caution ('do not retry after success'). It stops short of naming an alternative sibling (e.g. open_quick_log, list_feeds) or a when-not-to-use beyond the user-intent condition, so it is clear context rather than full routing guidance.

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

All Nestling tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?