Skip to main content
Glama

Read a page of postalref.com

read
Read-onlyIdempotent

Read a page of postalref.com by its path. /glossary/ gives what USPS means by a term: its entry, with its kind and tier, the USPS words that define it and the page they're on, its other names, postalref's own explanation where it has one, and when USPS ended or renamed it, each with USPS's words; /glossary/, such as /glossary/mailer-id or /glossary/MID, gives the entries those words name, in the order search ranks them. /codes//, such as /codes/service-type-codes/055, gives a code's row as USPS prints it in the newest edition that lists it, the editions that list it and its history. /documents/ gives any document postalref holds, page by page as extracted, to quote, and /documents lists them. Any other path is a page of the site, given as its Markdown: a product page (/products/), a guide (/guides/), a code table's home (/codes/), a case (/cases/), a spec (/specs/), a topic (/topics/) or /changes. Quote whole sentences, word for word. A definition's words cite its document and page, and its read names the document and page to read for the sentences around them. A document's text, or a found context, which shows the whole sentence around the words or the lead-in with the list it opens, cites the revision's sha256, the PDF page and the words exactly; read another page found lists by its pdf number, or a part by its number, as page. When the text ends mid-sentence or mid-list, continued gives the rest of it from next, cited by its own page; when it ends mid-table, or a list goes on past continued, read next. A text without pages, a web page or a product page, reads in parts, and a quote from one cites no page.

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": {
      "path": "<path>"
    },
    "name": "read"
  }
}

Input Schema

NameRequiredDescriptionDefault
findNoWith /documents/<id>: words to find, as one phrase, or when no page has the phrase, each word anywhere on a page. Without `page`, the text read is the first pages that have them.
pageNoWith /documents/<id>: the first PDF page, sheet or part to read, counting from 1; absent with `find`, the pages that have the words. With /documents: the page of the list, 100 documents a page.
pathYesA path of postalref.com, as search and grep give each hit's `path`, or a page's address on the site: /glossary/mid, /glossary/mailer-id, /codes/service-type-codes/055, /documents/pub-199, /documents, /products/mid.
pagesNoWith /documents/<id>: how many to read, up to 5; 1 when absent.
revisionNoWith /documents/<id>: a revision's sha256, or its slug, such as 2026-07-02. The newest when absent.

Output Schema

NameRequiredDescriptionDefault
codeNo
listNo
pathYes
termNo
documentNo
markdownNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare a safe, idempotent read. Beyond that, the description discloses the return form (Markdown for site pages, extracted page-by-page text for documents), the citation model (sha256, PDF page, exact words), and the continuation semantics via `continued`/`next` — genuinely useful behavior an agent could not infer from the schema.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is one dense run-on paragraph with heavy quoting of field names (`continued`, `next`, `found`, `pdf`) that is hard to parse on a first read. Nearly every clause carries information, but the lack of sentence-level structure costs clarity.

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?

With an output schema present, return values needn't be explained, yet the description still covers what each path returns and how pagination and continuation work — enough for correct invocation. The continuation logic is stated but remains the least legible part of an otherwise complete definition.

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 schema already defines all five parameters. The description still adds meaning the schema lacks: the interplay between `find`, `page` and `pages` in continuation scenarios, and how a `pdf` number from `found` becomes a `page` argument.

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?

Opens with a specific verb and resource ('Read a page of postalref.com by its path') and then enumerates each path family and what it yields, so an agent knows exactly what this tool returns versus a search or grep hit.

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?

The description establishes clear usage context by mapping path shapes to outcomes and by telling the agent how to follow citations and continuations ('read another page `found` lists by its `pdf` number, or a part by its number, as `page`'). It does not explicitly say when to prefer search or grep instead, so it stops short of full when/when-not guidance.

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