Skip to main content
Glama

Get reading days

get_reading_days
Read-onlyIdempotent

Lists the page the reader reached on each day of one reading of a book in their ReadingRate library: for each day, the furthest page, the page they left off at, the pages read and the percent of their copy.

Use when the user asks how far they got each day, how many pages they read on which days, how long a book took them day by day, or wants a chart of their progress through a book. For the books themselves, their status and dates, use get_reading_history.

ReadingRate records each change of page from the time this history began, so days before logged_since are unknown, not unread. Days are counted in timezone: give the reader's IANA time zone when known (for example "Europe/London"); otherwise their notification setting is used, else UTC.

Examples:

  • {"book_id": ""}

  • {"book_id": "", "timezone": "Europe/London"}

  • {"book_id": "", "reading_number": 1}

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": {
      "book_id": "<book_id>"
    },
    "name": "get_reading_days"
  }
}

Input Schema

NameRequiredDescriptionDefault
book_idYesThe book's ReadingRate id or its library entry id
timezoneNoIANA time zone the days are counted in, for example "Europe/London"
reading_numberNoWhich reading: 1 for the first, 2 for a reread. Default: the latest

Output Schema

NameRequiredDescriptionDefault
bookYesThe book: id, slug, title, authors
daysYesOne entry per day with a page change, oldest first
noteNoWhat the days do and do not cover
statusNoread | reading | want_to_read | stopped
end_dateNo
timezoneNoThe time zone the days are counted in
start_dateNo
total_pagesNoPrinted pages in the reader's copy, without a roman-numbered introduction; percent counts the whole copy
current_pageNo
logged_sinceNoWhen the first page change of this reading was recorded; days before it are not known
reading_numberNoWhich reading of the book: 1 for the first, 2 for a reread
reverse_numberingNoThe book counts down to page 1: its furthest page each day is the lowest
current_page_labelNocurrent_page as the book prints it, e.g. "liv" or "10"
front_matter_pagesNoRoman-numbered pages at the front of the reader's copy (an introduction numbered i–lx is 60). When set, every page here counts from page i, and the *_label fields give the page as printed

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / status / description
      Previous value: -"read | reading | want_to_read | stopped | dnf"New value: +"read | reading | want_to_read | stopped"
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent and closed-world, but the description adds substantive context they cannot: data only exists from when this history began, so days before logged_since are unknown rather than unread. It also documents the timezone resolution chain (reader's IANA zone, else notification setting, else UTC), which materially affects results. The only gap is that it does not say what happens for a reading_number that does not exist.

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?

Purpose is front-loaded, then usage guidance, then a caveat, then examples — a sensible order with no filler sentences. The example block is somewhat redundant given a 100%-covered schema with three optional/one required parameter, which is the only reason this isn't a 5.

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?

An output schema exists, so return values need not be explained, and annotations carry the safety profile. The description still covers scope, the historical-data limitation, and timezone handling — everything an agent needs to call this correctly and interpret partial results.

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 adds meaning beyond the schema for timezone by explaining the fallback order when it is omitted. The reading_number and book_id semantics are largely restated from the schema, which keeps this below a 5.

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 sentence gives a specific verb and resource: it lists the furthest page, leave-off page, pages read and percent per day for one reading of one book. It also scopes the tool to a single reading and names the sibling it is not for (get_reading_history), so an agent can distinguish it without opening either schema.

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 enumerates concrete user intents that select this tool (how far each day, pages per day, how long a book took day by day, a progress chart) and explicitly routes the alternative case to get_reading_history. Both when-to-use and when-to-use-something-else are stated.

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.