Skip to main content
Glama

AstraNL Dutch counterparty check

read_with_receipt

Read a published protocol result and request an entry in the public transparency log holding a digest of the answer. The receipt is not a quote, not a price guarantee and not proof of delivery. Nothing is bought, paid or sent to a counterparty; publication reads may contact external sources. Confirm transition.receipt.reference through MCP verify_astranl with ref, A2A SendMessage with message.metadata.skill=verify and ref in a data part, or HTTPS GET https://astranl.com/api/protocol/read/verify?ref=REFERENCE. An optional answer_sha256 checks the answer digest. A receipt may be unavailable or pending log inclusion; confirmation states its current limits.

Input Schema

NameRequiredDescriptionDefault
readYes
argumentsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, and the description genuinely explains the non-read-only nature: a log entry is requested and publication reads may contact external sources. It adds limits the annotations cannot express—the receipt may be unavailable or pending log inclusion, and confirmation states those limits. It stops short of saying each call creates a distinct log entry (the source of non-idempotency) or what the receipt payload contains.

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, which is right, but the body is dense and partly redundant: 'not a quote, not a price guarantee and not proof of delivery' overlaps heavily with 'Nothing is bought, paid or sent to a counterparty'. The three-route verification sentence is long and detail-heavy relative to how little is said about the read modes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a high-complexity tool—nested oneOf, four dispatch modes, no output schema—and the description covers only the generic receipt flow. It never describes what each read mode returns or which arguments each branch needs, so an agent cannot call it correctly for three of the four modes without reverse-engineering the schema. The receipt-confirmation detail is good but leaves the core dispatch underspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is reported at 0% against a nested oneOf with per-branch required fields (demand, site, ref). The description explains only answer_sha256 as an optional answer-digest check and leaves the read discriminator's four values and each branch's arguments entirely unexplained. With such low structured coverage, the description should carry the branch semantics and does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening states a concrete verb pair and resource: read a published protocol result and request a transparency-log entry holding its digest. But the tool is a polymorphic dispatcher over read=find_offers|network_door|coordination_contract|verify_astranl, and the description never says what those modes are or how this differs from the sibling tools that carry the same names. An agent knows the general intent but not which mode to select or why this wrapper exists alongside find_offers and verify_astranl.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the disclaimers ('not a quote, not a price guarantee, not proof of delivery', 'nothing is bought, paid or sent') and by the three explicit follow-up routes for confirming a reference via verify_astranl, A2A SendMessage, or HTTPS GET. There is no explicit statement of when to choose this tool over calling find_offers or verify_astranl directly, and no prerequisite or exclusion conditions for the tool itself.

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